© 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. 4308
    Prev
    Next
    INDEX
    Explanations

    regular expressions and related code snippets, as well as questions and exclamations in other languages and some abbreviations

    oai_token-act-pair · gemini-2.0-flash

    quoi

    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
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -1.13
     مشين
    -1.11
    :✨
    -1.00
    SequentialGroup
    -0.94
    oredCriteria
    -0.92
    Personensuche
    -0.91
     EconPapers
    -0.91
    ScopeManager
    -0.90
    fromnode
    -0.90
    matchCondition
    -0.88
    POSITIVE LOGITS
    ?
    0.68
     ?
    0.58
    ?.
    0.57
    ??
    0.50
    as
    0.49
     filles
    0.48
    ?”
    0.47
    ?"
    0.47
     How
    0.46
    ie
    0.45
    Activations Density 0.578%

    No Known Activations