© 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. 9512
    Prev
    Next
    INDEX
    Explanations

    automotive specifications, including engine details, horsepower, and dimensions.

    oai_token-act-pair · gemini-2.0-flash

    engine power

    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
    kaŭ
    -0.53
    setupUi
    -0.50
    BeginInit
    -0.48
    addContainerGap
    -0.48
    icide
    -0.48
     arşivlendi
    -0.48
    heat
    -0.47
    rouille
    -0.46
     متعلقه
    -0.46
    navigateTo
    -0.46
    POSITIVE LOGITS
    tonode
    0.61
     الحره
    0.61
     MainAxisSize
    0.59
    Datuak
    0.57
    migrationBuilder
    0.57
    __.__
    0.56
     незавершена
    0.56
    الإنجليزية
    0.54
     AssemblyCompany
    0.53
    setopt
    0.52
    Activations Density 0.321%

    No Known Activations