© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9600
    Prev
    Next
    INDEX
    Explanations

    numerical expressions, especially mathematical calculations and references to months

    oai_token-act-pair · gemini-2.0-flash

    math/code snippet

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     mxArray
    -0.85
     فريبيس
    -0.83
    __(/*!
    -0.79
    MigrationBuilder
    -0.76
     nahilalakip
    -0.74
     Paglinawan
    -0.69
    PerformLayout
    -0.69
    曖昧さ回避
    -0.65
     transfieras
    -0.63
    SourceChecksum
    -0.62
    POSITIVE LOGITS
    stream
    0.52
    STREAM
    0.49
     Stream
    0.48
     muualla
    0.48
    Stream
    0.46
    clyde
    0.43
    hip
    0.42
    WithIdentifier
    0.41
     sente
    0.41
     BitmapFactory
    0.41
    Activations Density 2.371%

    No Known Activations