© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2048
    Prev
    Next
    INDEX
    Explanations

    a jumble of seemingly unrelated terms in medical papers, java code and legal documents.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     kasarigan
    -0.94
    featureID
    -0.82
     protoimpl
    -0.74
     مشين
    -0.73
    principalTable
    -0.72
     typelib
    -0.72
    parsedMessage
    -0.71
     iNdEx
    -0.69
     ویکی‌پدیا
    -0.67
    Personensuche
    -0.66
    POSITIVE LOGITS
    onoi
    0.54
     hänen
    0.54
     Mendes
    0.51
     Shun
    0.51
     Athan
    0.50
     RoutedEventArgs
    0.49
    loom
    0.47
    imanapun
    0.47
     alcan
    0.47
     microp
    0.46
    Activations Density 37.544%

    No Known Activations