© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 180039
    Prev
    Next
    INDEX
    Explanations

    Donald

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    লাইন
    0.39
    গিত
    0.38
    羚
    0.38
     jade
    0.36
    綬
    0.36
    ライン
    0.36
     الخط
    0.36
     газо
    0.36
     tendered
    0.36
    ("[
    0.35
    POSITIVE LOGITS
     W
    0.97
    W
    0.80
     ال
    0.54
     डब्ल्यू
    0.51
    Ｗ
    0.51
    w
    0.51
     w
    0.50
    弇
    0.45
    Donald
    0.42
    nW
    0.42
    Activations Density 0.018%

    No Known Activations