© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15328
    Prev
    Next
    INDEX
    Explanations

    numerical data about pharmaceutical dosages or genetic lineages

    oai_token-act-pair · gemini-2.0-flash

    tokens indicating quantities or measurements

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

    vaccination

    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
     ModelExpression
    -0.83
    AnchorTagHelper
    -0.81
    StoryboardSegue
    -0.78
    DoubleQuotes
    -0.73
    ContentAsync
    -0.70
    tagext
    -0.67
    WireFormatLite
    -0.66
    蚪
    -0.65
    MigrationBuilder
    -0.64
    帖最后由
    -0.62
    POSITIVE LOGITS
    }>
    0.50
     soft
    0.49
     boca
    0.49
    coch
    0.47
     shots
    0.46
     Bach
    0.46
     shot
    0.46
     wide
    0.45
    acha
    0.45
     front
    0.45
    Activations Density 6.307%

    No Known Activations