© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 127782
    Prev
    Next
    INDEX
    Explanations

    spark app name

    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_37_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
     Garry
    0.38
     mía
    0.37
     ganado
    0.35
     Lexikon
    0.35
     thuyết
    0.35
    noise
    0.35
     mud
    0.34
     Fern
    0.34
    鍊
    0.34
     прида
    0.34
    POSITIVE LOGITS
    ంధ్ర
    0.44
    neis
    0.39
    🇳
    0.39
     ಗ್ರಾ
    0.37
    सदीय
    0.36
     jumpsuit
    0.36
    плы
    0.36
    coroutines
    0.36
     frem
    0.36
     alliance
    0.36
    Activations Density 0.001%

    No Known Activations