© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 113382
    Prev
    Next
    INDEX
    Explanations

    nothing else

    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_2_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
    X
    1.30
    ﺔ
    1.20
    _
    1.13
    ের
    1.13
    ća
    1.12
    ы
    1.12
     abandon
    1.05
     antivirus
    1.04
    很
    1.03
    at
    1.02
    POSITIVE LOGITS
    ס
    1.27
    ます
    0.96
    مع
    0.92
    種類
    0.91
    ्‍यादा
    0.87
    おお
    0.85
    設定
    0.82
    delen
    0.82
    ด
    0.82
    ד
    0.82
    Activations Density 0.001%

    No Known Activations