© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 92049
    Prev
    Next
    INDEX
    Explanations

    policy development or political order

    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_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ור
    0.94
    0
    0.86
    UT
    0.75
    am
    0.74
    4
    0.74
    ра
    0.72
    B
    0.72
    UQ
    0.72
    H
    0.71
    un
    0.71
    POSITIVE LOGITS
    t
    0.68
    -
    0.68
    /
    0.64
    ität
    0.57
     processions
    0.57
    kken
    0.56
     Supporters
    0.55
     summits
    0.54
    ivational
    0.54
     regimens
    0.54
    Activations Density 0.001%

    No Known Activations