© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14534
    Prev
    Next
    INDEX
    Explanations

    the word "discharge" and words related to debt/financial responsibility.

    oai_token-act-pair · gemini-2.0-flash

    discharge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     the
    -0.77
    at
    -0.63
     at
    -0.61
    time
    -0.60
     over
    -0.59
     on
    -0.59
     am
    -0.58
     near
    -0.57
    so
    -0.57
     in
    -0.57
    POSITIVE LOGITS
    MigrationBuilder
    1.19
     ModelExpression
    1.18
    ^(@)
    1.16
     Efq
    1.15
     depositphotos
    1.12
    aarrggbb
    1.10
     itſelf
    1.09
     MainAxisSize
    1.07
     مشين
    1.06
     Jefus
    1.06
    Activations Density 0.915%

    No Known Activations