© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 116437
    Prev
    Next
    INDEX
    Explanations

    utils.import, def __

    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_38_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
    sé
    0.40
    ereza
    0.38
    igné
    0.37
    बानी
    0.37
    ************/
    0.36
    că
    0.36
    pocket
    0.36
    swift
    0.36
    igue
    0.35
    صیٰ
    0.35
    POSITIVE LOGITS
     숫
    0.41
     스타
    0.39
     شماره
    0.37
     순간
    0.36
    වැ
    0.35
    තු
    0.35
     함수
    0.35
     neuest
    0.35
     største
    0.35
    庤
    0.35
    Activations Density 0.000%

    No Known Activations