© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12505
    Prev
    Next
    INDEX
    Explanations

    lines of code defining parameters for file installation

    oai_token-act-pair · gemini-2.0-flash

    programming and technical terminology

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

    Currency codes

    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
     griega
    -0.79
     africains
    -0.74
     grecque
    -0.72
     japonesa
    -0.71
     alemana
    -0.66
     británica
    -0.65
     asiática
    -0.65
     africano
    -0.64
     japonais
    -0.64
     coreano
    -0.63
    POSITIVE LOGITS
     مشين
    0.79
    PerformLayout
    0.74
     nahilalakip
    0.71
    ReusableCell
    0.64
     ProtoMessage
    0.61
    ArrowToggle
    0.60
    ?>">
    0.57
     insuffisamment
    0.57
    findpost
    0.56
    DoubleQuotes
    0.55
    Activations Density 1.407%

    No Known Activations