© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11095
    Prev
    Next
    INDEX
    Explanations

    statistical data, especially percentages, and comparisons

    oai_token-act-pair · gemini-2.0-flash

    statistics, demographics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    tagHelperRunner
    -0.77
     auroit
    -0.65
     étudiant
    -0.57
     étoit
    -0.57
     fausse
    -0.55
     scheda
    -0.55
    MigrationBuilder
    -0.54
     feroit
    -0.54
     namanya
    -0.53
     saira
    -0.53
    POSITIVE LOGITS
    XmlAccessorType
    0.75
     ModelExpression
    0.63
    Carriera
    0.62
     وتسجيلات
    0.60
    XmlEnum
    0.54
    emang
    0.53
    Trama
    0.52
     bran
    0.51
    quel
    0.50
    erals
    0.50
    Activations Density 2.506%

    No Known Activations