© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9405
    Prev
    Next
    INDEX
    Explanations

    various forms of the verb "cut" and/or mentions of fingers

    oai_token-act-pair · gemini-2.0-flash

    cut

    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
    Negative Logits
     cut
    -2.95
     Cut
    -2.69
    cut
    -2.69
    Cut
    -2.61
     cuts
    -2.45
     CUT
    -2.34
    cuts
    -2.31
    CUT
    -2.27
     cutting
    -2.25
     Cuts
    -2.19
    POSITIVE LOGITS
    ThroughAttribute
    0.48
    чко
    0.46
     compagn
    0.46
     désolés
    0.44
     riservata
    0.43
    sizeCache
    0.42
    ginas
    0.41
     Hinter
    0.41
    šina
    0.40
    PANY
    0.40
    Activations Density 11.464%

    No Known Activations