© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30239
    Prev
    Next
    INDEX
    Explanations

    multilingual descriptions and questions

    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_31_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
     dựng
    0.33
     channel
    0.32
     terlalu
    0.32
     cavity
    0.32
    渋
    0.32
     buruk
    0.31
     dul
    0.31
     caused
    0.31
     rainbow
    0.31
    ⼯
    0.31
    POSITIVE LOGITS
     описание
    0.39
    umma
    0.39
    IVOS
    0.37
    灬
    0.37
    interpretation
    0.36
     ಅಥವಾ
    0.36
     ವಿವರ
    0.36
    interpol
    0.36
    responses
    0.35
    ರ್ಥ
    0.35
    Activations Density 0.002%

    No Known Activations