© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10467
    Prev
    Next
    INDEX
    Explanations

    mathematical notations with 'p' to indicate statistical significance

    oai_token-act-pair · gemini-2.0-flash

    statistical significance indicators

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

    P

    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
     Мексичка
    -0.74
    principalColumn
    -0.59
     POSTS
    -0.59
    InitVars
    -0.59
    ÚBL
    -0.59
    रीदारी
    -0.59
     Exacts
    -0.58
    setPointSize
    -0.57
    jooq
    -0.57
    RunAsync
    -0.57
    POSITIVE LOGITS
     less
    0.57
     Less
    0.49
    +#+
    0.48
    Less
    0.47
    unn
    0.46
     مشين
    0.46
     ناب
    0.45
    GEBURTSDATUM
    0.43
    rend
    0.43
    imper
    0.43
    Activations Density 3.282%

    No Known Activations