© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83760
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    ক
    0.68
     Thoreau
    0.62
    یک
    0.60
    In
    0.59
     of
    0.59
    य
    0.57
     Of
    0.56
    كتب
    0.56
    目的是
    0.56
     为
    0.55
    POSITIVE LOGITS
    ts
    0.52
    tt
    0.52
    ta
    0.50
    fon
    0.49
    ens
    0.49
    gunakan
    0.49
    ao
    0.48
    disable
    0.48
    mack
    0.48
    re
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.