© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25327
    Prev
    Next
    INDEX
    Explanations

    special characters or code delimiters

    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_10_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
    u
    1.16
    ın
    0.82
    it
    0.81
    í
    0.80
    in
    0.77
    ının
    0.69
     Zustand
    0.65
    ו
    0.65
    l
    0.63
    uak
    0.63
    POSITIVE LOGITS
     aument
    0.71
    (
    0.70
    స్‌
    0.69
    也
    0.68
     études
    0.68
    _
    0.67
    ليس
    0.67
     évaluations
    0.65
    ीकृत
    0.64
     étude
    0.64
    Activations Density 0.038%

    No Known Activations