© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10199
    Prev
    Next
    INDEX
    Explanations

    code-related tokens, especially those present in C++ or similar languages

    oai_token-act-pair · gemini-2.0-flash

    Code and equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    tvguidetime
    -0.81
    NUMX
    -0.76
     Jefus
    -0.69
     itſelf
    -0.67
    >\<^
    -0.66
     myſelf
    -0.65
     XNUMX
    -0.64
    neſs
    -0.64
     becauſe
    -0.63
    leſs
    -0.63
    POSITIVE LOGITS
    InstrumentedTest
    0.52
    rev
    0.48
    ver
    0.46
    X
    0.45
    sys
    0.45
     pstmt
    0.44
    T
    0.44
    _
    0.44
    strijd
    0.44
     ante
    0.44
    Activations Density 1.701%

    No Known Activations