Single cell RNA-Seq (scRNA-seq) studies often profile upward of thousands of cells in heterogeneous environments. Current methods for characterizing cells perform unsupervised analysis followed by assignment using a small set of known marker genes. Such approaches are limited to a few, well characterized cell types. To enable large scale supervised characterization we developed an automated pipeline to download, process, and annotate publicly available scRNA-seq datasets. We extended supervised neural networks to obtain efficient and accurate representations for scRNA-seq data. We implemented a web server that compares new datasets to collected data employing fast matching methods in order to determine cell types, key genes, similar prior studies, and more. We applied our pipeline to process over 500 different studies with over 300 unique cell types. A case study of neural degeneration data highlights the ability of the web server to identify differences between cell type distributions in healthy and diseased mice.