© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 30367
    Prev
    Next
    INDEX
    Explanations

    Guangdong

    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_10_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
     azimuthal
    0.65
    枻
    0.59
     azimuth
    0.57
    klassen
    0.56
    LOTREntity
    0.56
     الداله
    0.56
     allusion
    0.55
     monadic
    0.55
    VarArgs
    0.55
    Penumpang
    0.55
    POSITIVE LOGITS
    ل
    0.96
    л
    0.86
    د
    0.85
    ت
    0.78
    न
    0.73
    ى
    0.73
     заяви
    0.72
    н
    0.69
    غ
    0.69
    б
    0.68
    Activations Density 0.000%

    No Known Activations