© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4466
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    oai_token-act-pair · gemini-2.0-flash

    Quotation/Dollar Sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Rüyada
    -0.66
    setopt
    -0.59
     toString
    -0.58
    clearfix
    -0.55
    malink
    -0.55
    tvguidetime
    -0.54
    YLE
    -0.51
    ädie
    -0.51
    Köszönöm
    -0.50
    migrationBuilder
    -0.50
    POSITIVE LOGITS
    <bos>
    0.66
     quæ
    0.63
    ."],
    0.61
    ."),
    0.59
    }(),
    0.57
    исленность
    0.57
    mtrl
    0.57
    elemField
    0.57
    kloped
    0.56
     giuri
    0.56
    Activations Density 0.977%

    No Known Activations