© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3271
    Prev
    Next
    INDEX
    Explanations

    capitalized words, particularly those relating to study names or trademarks, and numbers within legal citations

    oai_token-act-pair · gemini-2.0-flash

    numbered lists in reports

    np_max-act · 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
    áv
    -0.44
    ineno
    -0.43
     fix
    -0.41
    readlines
    -0.40
    μος
    -0.40
     Cancellation
    -0.40
     Emissions
    -0.39
    gesehen
    -0.37
    kmäler
    -0.36
     Fix
    -0.35
    POSITIVE LOGITS
    новништво
    1.05
     estimés
    1.00
     للاسماء
    0.92
    出版年
    0.91
    참고
    0.88
     kasarigan
    0.84
     >=",
    0.84
    Geplaatst
    0.83
     Paglinawan
    0.82
    ItemBackground
    0.79
    Activations Density 0.944%

    No Known Activations