© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 152941
    Prev
    Next
    INDEX
    Explanations

    client/prospect status or actions

    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_23_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
     jinfo
    0.40
    нен
    0.39
     എന്നു
    0.39
    ﻙ
    0.39
    $，
    0.39
    лән
    0.38
    underset
    0.37
     بی‌
    0.37
    िज़
    0.37
    POE
    0.36
    POSITIVE LOGITS
     Spotify
    0.43
     Marquis
    0.43
    ickers
    0.40
     discussed
    0.40
    ەت
    0.40
    睞
    0.39
     definitiva
    0.39
     gang
    0.38
     ader
    0.38
    ේව
    0.38
    Activations Density 0.001%

    No Known Activations