© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3382
    Prev
    Next
    INDEX
    Explanations

    titles of books and the information about their publication

    oai_token-act-pair · gemini-2.0-flash

    book excerpts

    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
     record
    -0.59
    헌
    -0.52
    record
    -0.47
    
    -0.46
     Record
    -0.46
    Record
    -0.46
     graduate
    -0.45
    رشف
    -0.45
     وتسجيلات
    -0.43
    twimg
    -0.42
    POSITIVE LOGITS
    AppendLine
    0.64
     Theſe
    0.63
    urlpatterns
    0.63
    PointerException
    0.63
     iArr
    0.62
    virons
    0.62
     whiteColor
    0.61
    Inggris
    0.60
    NetworkInfo
    0.60
     RoutedEventArgs
    0.60
    Activations Density 0.431%

    No Known Activations