© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9342
    Prev
    Next
    INDEX
    Explanations

    technical language related to manufacturing, science, and engineering

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Datuak
    -0.91
    IntoConstraints
    -0.89
     للاسماء
    -0.86
     tartalomajánló
    -0.85
    Autoritní
    -0.83
     المعيارى
    -0.82
    StructEnd
    -0.81
    
    -0.80
    TagMode
    -0.80
    MigrationBuilder
    -0.77
    POSITIVE LOGITS
    wi
    0.47
     OK
    0.47
    かせ
    0.46
     wo
    0.43
     ä
    0.43
     help
    0.43
    NA
    0.42
     tri
    0.42
     services
    0.42
    parsedMessage
    0.42
    Activations Density 3.112%

    No Known Activations