© 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. 3843
    Prev
    Next
    INDEX
    Explanations

    words related to health, hygiene, and the spread of disease

    oai_token-act-pair · gemini-2.0-flash

    sanitation and hygiene

    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
     szóci
    -0.47
     .
    -0.42
    /~
    -0.41
    GRect
    -0.41
    addCriterion
    -0.41
     trời
    -0.40
    چار
    -0.40
    ^{-}$
    -0.39
    DIPSETTING
    -0.39
     Ag
    -0.38
    POSITIVE LOGITS
    <bos>
    0.93
     myſelf
    0.90
    OGND
    0.83
    ſelf
    0.81
     ſhe
    0.81
     itſelf
    0.81
    Coronavirus
    0.79
     Jefus
    0.79
     themſelves
    0.79
     Quarantine
    0.75
    Activations Density 1.017%

    No Known Activations