© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9738
    Prev
    Next
    INDEX
    Explanations

    words related to user data, privacy, and online tracking

    oai_token-act-pair · gemini-2.0-flash

    aggregated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     betweenstory
    -0.58
    ViewImports
    -0.53
    hbase
    -0.48
     genes
    -0.45
    EndInit
    -0.44
     سن
    -0.44
     terms
    -0.43
    writeHead
    -0.42
     elő
    -0.42
    viertel
    -0.42
    POSITIVE LOGITS
    Попис
    0.73
    WireFormatLite
    0.71
     Perſ
    0.66
     chi̍t
    0.66
     disambiguazione
    0.65
     виправивши
    0.65
     EconPapers
    0.63
    addCriterion
    0.63
    ChildScrollView
    0.62
    RTLD
    0.62
    Activations Density 0.773%

    No Known Activations