© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3841
    Prev
    Next
    INDEX
    Explanations

    mentions of clothes or costumery, especially the verb *to wear* and the noun *uniform*

    oai_token-act-pair · gemini-2.0-flash

    wear

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     wear
    -2.47
     wears
    -2.09
     Wear
    -2.08
     wore
    -2.06
    wear
    -2.05
    Wear
    -2.05
     wearing
    -2.03
     WEAR
    -1.98
     worn
    -1.81
     Wearing
    -1.80
    POSITIVE LOGITS
    참고
    0.69
    IntoConstraints
    0.67
    XmlAccessType
    0.54
    LookAnd
    0.52
     esternos
    0.52
    billi
    0.50
    modelBuilder
    0.50
    новништво
    0.49
     Roskov
    0.49
     Trou
    0.49
    Activations Density 1.331%

    No Known Activations