© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 203445
    Prev
    Next
    INDEX
    Explanations

    discord.py code imports

    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_12_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
    akarane
    0.57
     =-\
    0.57
    atoti
    0.56
    ীবনী
    0.56
    фель
    0.56
    ्हान
    0.56
    珢
    0.55
    ActionsForRule
    0.55
    楂
    0.55
    ืช
    0.55
    POSITIVE LOGITS
     &
    0.70
    A
    0.70
     V
    0.68
    L
    0.66
     L
    0.63
     ~
    0.62
    ↵↵
    0.61
    na
    0.61
     by
    0.60
    U
    0.59
    Activations Density 0.005%

    No Known Activations