© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7037
    Prev
    Next
    INDEX
    Explanations

    text from financial reports

    oai_token-act-pair · gemini-2.0-flash

    auditing accounting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     ErrIntOverflow
    -0.56
     sobriety
    -0.54
     HasFactory
    -0.52
    lapsingToolbar
    -0.52
    DebuggerNonUser
    -0.52
     intern
    -0.51
     OnTriggerEnter
    -0.50
    Последние
    -0.50
    ВП
    -0.50
    enumi
    -0.49
    POSITIVE LOGITS
    IsContent
    0.57
    readObject
    0.54
    ContentAsync
    0.51
     lenker
    0.50
    webElementXpaths
    0.48
    mth
    0.48
    $",
    0.48
    ViewImports
    0.47
     [{
    0.46
    bsch
    0.46
    Activations Density 0.894%

    No Known Activations