© 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. 36493
    Prev
    Next
    INDEX
    Explanations

    data structure names

    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
     Kala
    0.28
     мою
    0.26
    евского
    0.26
     Postage
    0.26
    Floral
    0.26
    ગર
    0.26
     Delegates
    0.26
    🐕
    0.26
     Floral
    0.25
     Trades
    0.25
    POSITIVE LOGITS
    packageName
    0.29
     packageName
    0.28
     dalej
    0.27
     potens
    0.26
    र्चे
    0.26
    忍者
    0.25
     package
    0.25
     decomp
    0.25
    诗人
    0.25
     سرمایہ
    0.25
    Activations Density 0.003%

    No Known Activations