© 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. 40655
    Prev
    Next
    INDEX
    Explanations

    slavic, arabic, or place name endings

    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
    е
    1.04
    ра
    0.83
    и
    0.81
    ים
    0.80
    pel
    0.73
    м
    0.73
    а
    0.73
    c
    0.71
    ↵
    0.70
    ch
    0.70
    POSITIVE LOGITS
    O
    0.92
    U
    0.78
    OO
    0.75
    AN
    0.71
    UT
    0.70
    Nach
    0.70
    SUN
    0.70
    V
    0.69
    OT
    0.69
    M
    0.68
    Activations Density 0.003%

    No Known Activations