© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 238370
    Prev
    Next
    INDEX
    Explanations

    where gravity is so strong

    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_32_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    することも
    0.41
    гъл
    0.38
     tung
    0.38
     это
    0.38
    ㄸ
    0.37
     만나
    0.37
     tracking
    0.37
     pingis
    0.37
     Tracking
    0.37
    это
    0.37
    POSITIVE LOGITS
    क्तियों
    0.38
    <unused8>
    0.38
     казіно
    0.38
    oretum
    0.36
    ഞ്ഞു
    0.36
    ommen
    0.35
    삼성
    0.35
    lepiej
    0.35
    ancourt
    0.35
    AMSUNG
    0.34
    Activations Density 0.002%

    No Known Activations