© 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. 36861
    Prev
    Next
    INDEX
    Explanations

    describe

    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
    可以说是
    0.77
    說是
    0.68
    可以说
    0.66
     disebut
    0.65
     nazy
    0.62
     বলা
    0.61
     say
    0.60
    称
    0.59
     dikatakan
    0.58
    say
    0.57
    POSITIVE LOGITS
    陴
    0.40
     കണ്ട
    0.35
    दुर्
    0.35
     الأز
    0.35
    甶
    0.34
     बदली
    0.34
     صفحۀ
    0.33
     Fin
    0.33
     وړ
    0.33
    :/
    0.33
    Activations Density 0.024%

    No Known Activations