© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1029
    Prev
    Next
    INDEX
    Explanations

    multilingual prompts

    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_39_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
    ilizce
    0.48
    ᅭ
    0.44
    하시면
    0.43
     doing
    0.39
    ᱛ
    0.39
     해도
    0.38
    handlung
    0.38
    하다고
    0.38
    됬
    0.38
     ചെയ്
    0.38
    POSITIVE LOGITS
     Зе
    0.43
    interpolation
    0.38
    paration
    0.36
    intercept
    0.35
     ovo
    0.35
    dic
    0.35
     Subdivision
    0.34
    れる
    0.34
    hibit
    0.34
     интер
    0.34
    Activations Density 0.019%

    No Known Activations