© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14439
    Prev
    Next
    INDEX
    Explanations

    text related to collecting and examining bodily waste, medical procedures, and bodily fluids

    oai_token-act-pair · gemini-2.0-flash

    Code tokens

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    numerusform
    -0.57
    }{*}{
    -0.56
    <tbody>
    -0.52
     것이다
    -0.47
     uniqu
    -0.46
    ніципалі
    -0.46
    extAlignment
    -0.46
     bauer
    -0.46
     Tinder
    -0.45
    LIB
    -0.45
    POSITIVE LOGITS
     AssemblyCompany
    0.69
     فريبيس
    0.67
     GenerationType
    0.63
    XtraGrid
    0.55
    InjectAttribute
    0.55
    queryInterface
    0.53
    تقاوى
    0.52
     initComponents
    0.52
    makeConstraints
    0.52
     typelib
    0.52
    Activations Density 2.399%

    No Known Activations