© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1881
    Prev
    Next
    INDEX
    Explanations

    code-related tokens and math formulas

    oai_token-act-pair · gemini-2.0-flash

    Code, math, foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    WireFormatLite
    -0.78
     مشين
    -0.68
    omitempty
    -0.63
     and
    -0.63
     AssemblyCulture
    -0.61
    outState
    -0.61
     дописавши
    -0.59
    tvguidetime
    -0.59
    WebServlet
    -0.59
     mène
    -0.58
    POSITIVE LOGITS
    roides
    0.52
     د
    0.48
    πα
    0.47
    zoic
    0.45
    ป
    0.45
     huyền
    0.44
    ՝
    0.43
     loro
    0.42
    ddots
    0.42
     пар
    0.42
    Activations Density 4.074%

    No Known Activations