© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1784
    Prev
    Next
    INDEX
    Explanations

    code diffs

    oai_token-act-pair · gemini-2.0-flash

    diff logs or code changes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     */
    -0.67
     XNUMX
    -0.58
    ']>
    -0.57
     VIDEOTAPE
    -0.57
    ?
    -0.56
    ಷ್
    -0.56
    enumi
    -0.56
     $)
    -0.55
     **/
    -0.54
     }}(
    -0.54
    POSITIVE LOGITS
    Personensuche
    0.63
    WebElementEntity
    0.56
     calldata
    0.53
    iastes
    0.52
     pageContext
    0.52
    ifferentiated
    0.50
     endwhile
    0.49
    amssymb
    0.49
    련
    0.48
     Boyce
    0.47
    Activations Density 1.302%

    No Known Activations