© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5669
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs, especially forms of "do", "will", and "to"

    oai_token-act-pair · gemini-2.0-flash

    do

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    don
    -0.74
     don
    -0.71
    帖最后由
    -0.69
    Don
    -0.64
     Don
    -0.64
     DON
    -0.60
     prácti
    -0.58
     же
    -0.57
    doesn
    -0.57
    DON
    -0.57
    POSITIVE LOGITS
    ScopeManager
    0.77
    RenderAtEndOf
    0.65
     ModelExpression
    0.60
    PreExecute
    0.60
    UpInside
    0.57
    MigrationBuilder
    0.57
     GenerationType
    0.56
    HtmlAttribute
    0.53
     bpy
    0.53
     arşivlendi
    0.52
    Activations Density 3.723%

    No Known Activations