© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206844
    Prev
    Next
    INDEX
    Explanations

    year

    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_20_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
    ❄
    0.30
     ಮತ್ತು
    0.29
    чёт
    0.29
     сохранить
    0.29
     διάρκ
    0.28
     чыныгы
    0.28
    WithFieldContext
    0.27
    шать
    0.27
    StaticHandler
    0.27
     эффек
    0.26
    POSITIVE LOGITS
    重
    0.24
     Tay
    0.24
     Te
    0.24
     Freighter
    0.23
     Bis
    0.23
     System
    0.23
     Gim
    0.22
    Te
    0.22
     maire
    0.22
     Cie
    0.22
    Activations Density 0.005%

    No Known Activations