© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9537
    Prev
    Next
    INDEX
    Explanations

    fragments from a question and answer section of text

    oai_token-act-pair · gemini-2.0-flash

    reuse

    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
    Tembelea
    -0.64
     виправивши
    -0.63
     שוליים
    -0.62
     MonoBehaviour
    -0.60
    zzleHttp
    -0.59
    indd
    -0.57
    GeoNames
    -0.57
    <?,
    -0.56
    withstanding
    -0.56
    ArgumentParser
    -0.54
    POSITIVE LOGITS
    googleapis
    0.52
    readLine
    0.50
    ্যা
    0.45
    transient
    0.43
    Portail
    0.43
    行政区划
    0.43
    hyrchwyd
    0.43
    QMetaType
    0.43
    epiece
    0.42
    ->
    0.41
    Activations Density 1.356%

    No Known Activations