© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54223
    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_55_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
     narrows
    0.40
     Packet
    0.39
    の方は
    0.39
    riez
    0.38
     생각이
    0.38
    श्त
    0.38
    Ắ
    0.38
    ificat
    0.37
     AFFAIRS
    0.37
     empowers
    0.37
    POSITIVE LOGITS
     Blume
    0.45
     knights
    0.35
    étude
    0.35
     フランス
    0.34
     Berkshire
    0.33
    鴿
    0.33
     stage
    0.33
    鳧
    0.33
     }[
    0.33
     স্বাধীন
    0.33
    Activations Density 0.000%

    No Known Activations