© 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. 9788
    Prev
    Next
    INDEX
    Explanations

    code snippets and XML or similar markup code

    oai_token-act-pair · gemini-2.0-flash

    Code symbols

    np_max-act · 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
    <bos>
    -0.59
    apimachinery
    -0.50
     saying
    -0.50
    noaa
    -0.47
     Asking
    -0.45
     confé
    -0.44
     asking
    -0.44
    saying
    -0.43
    ื่อง
    -0.43
     Borrow
    -0.43
    POSITIVE LOGITS
    MemoryWarning
    0.78
     BorderSide
    0.73
     BoxDecoration
    0.73
     BorderRadius
    0.69
    MIDDLEWARE
    0.65
     ?>/
    0.65
    StructEnd
    0.63
    __;
    0.62
    جغرافيا
    0.61
     EconPapers
    0.60
    Activations Density 0.379%

    No Known Activations