© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36552
    Prev
    Next
    INDEX
    Explanations

    function parameter types

    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_11_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
    ’
    0.50
    yon
    0.49
    ©
    0.45
    *
    0.44
    ISH
    0.44
    س
    0.43
     committed
    0.43
    ക്ട
    0.43
    郧
    0.43
     integrate
    0.42
    POSITIVE LOGITS
    ssä
    0.47
     شاعری
    0.47
     malah
    0.44
    ಾದರೂ
    0.44
    shifted
    0.44
    गारी
    0.44
     settimana
    0.44
    чения
    0.44
    essä
    0.44
    salad
    0.44
    Activations Density 0.008%

    No Known Activations