© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6300
    Prev
    Next
    INDEX
    Explanations

    words related to community and local areas

    oai_token-act-pair · gemini-2.0-flash

    community-related concepts

    np_token-act-pair-logits · gpt-4o-mini

    community

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    featureID
    -0.56
     combineReducers
    -0.50
    LElement
    -0.50
    ęgn
    -0.48
    AsyncTask
    -0.47
    PAIGN
    -0.47
     ویکی‌پدیای
    -0.46
    ButterKnife
    -0.46
    peth
    -0.46
     ronda
    -0.45
    POSITIVE LOGITS
    rungsseite
    0.90
     estekak
    0.72
     Audiodateien
    0.65
    IsContent
    0.62
    TagMode
    0.55
    AndEndTag
    0.55
    frc
    0.54
    ContentAsync
    0.54
     gynhyrchwyd
    0.52
     للمعارف
    0.52
    Activations Density 5.832%

    No Known Activations