© 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. 141892
    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
    i
    1.04
     héro
    0.98
     كن
    0.97
     كانوا
    0.95
    ле
    0.93
     وي
    0.89
     كان
    0.89
     добав
    0.89
     الاجتما
    0.88
    য়া
    0.87
    POSITIVE LOGITS
    в
    1.17
     powied
    1.11
    ס
    1.10
    어
    1.08
    স
    1.05
    in
    1.01
    ब
    1.01
    서
    0.97
    ਲ
    0.96
    ल
    0.96
    Activations Density 0.000%

    No Known Activations