© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48928
    Prev
    Next
    INDEX
    Explanations

    Python code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    query
    0.31
    Dependency
    0.31
     全部
    0.31
    expressions
    0.30
    )}$-
    0.30
     Maxwell
    0.29
    wheeled
    0.29
    cens
    0.29
    導
    0.29
    処理
    0.29
    POSITIVE LOGITS
     dah
    0.35
    тбол
    0.32
     al
    0.31
     bak
    0.30
     inaugural
    0.30
     bau
    0.30
    ungkinkan
    0.29
     cháu
    0.29
     sar
    0.29
    یکیشن
    0.29
    Activations Density 0.002%

    No Known Activations