© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1801
    Prev
    Next
    INDEX
    Explanations

    code documentation and code snippets, especially in C-like languages

    oai_token-act-pair · gemini-2.0-flash

    */

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     */
    -1.64
     */
    -1.55
    */
    -1.32
    <bos>
    -1.27
    */
    -1.25
    >*/
    -1.16
    )*/
    -1.10
     */;
    -1.10
     */
    -1.08
    }*/
    -1.07
    POSITIVE LOGITS
     Pelt
    0.47
     DPRD
    0.47
    thanh
    0.47
    στό
    0.46
    argout
    0.46
     Retention
    0.45
     onlyOwner
    0.45
    hados
    0.45
    entran
    0.44
     Nub
    0.44
    Activations Density 4.806%

    No Known Activations