© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 198394
    Prev
    Next
    INDEX
    Explanations

    common. / _ generated. / inc

    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_9_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
     αυτό
    0.85
    .
    0.80
    ről
    0.79
    ۔
    0.75
     Amended
    0.75
     lidí
    0.70
    Υ
    0.70
    ikopter
    0.69
     usuário
    0.66
     núcle
    0.66
    POSITIVE LOGITS
    на
    1.19
    м
    1.16
    в
    1.15
    ра
    0.96
    ка
    0.89
    р
    0.89
    م
    0.86
    up
    0.84
     as
    0.83
    ни
    0.82
    Activations Density 0.003%

    No Known Activations