© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 200266
    Prev
    Next
    INDEX
    Explanations

    ministry of health and security

    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_15_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
    </s>
    0.54
     店舗
    0.53
    PLAYER
    0.52
    KINS
    0.52
     Doyle
    0.50
     Бекер
    0.49
    Dónde
    0.48
    തിൽ
    0.47
     హైదర్
    0.47
    YK
    0.47
    POSITIVE LOGITS
    व
    0.55
     membros
    0.52
    ishes
    0.51
     miembros
    0.50
    ning
    0.50
    she
    0.50
    ಣಿ
    0.50
    திரு
    0.49
     lipids
    0.49
     legumes
    0.49
    Activations Density 0.000%

    No Known Activations