© 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. 206588
    Prev
    Next
    INDEX
    Explanations

    化学, 社会, 人生, 多様, 個性, 過去, 常

    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
    性質
    0.42
    ಪ್ಪು
    0.42
     सुपरस्टार
    0.41
     उपाय
    0.40
    ADIAN
    0.39
    ನ್ನೂ
    0.37
     Steady
    0.37
     steady
    0.37
    emph
    0.36
     *);
    0.36
    POSITIVE LOGITS
     Drain
    0.39
     Taj
    0.38
    дис
    0.38
     درب
    0.38
     orig
    0.37
    Cmd
    0.37
     zub
    0.37
     Payne
    0.37
    ஃப
    0.36
    ියේ
    0.36
    Activations Density 0.001%

    No Known Activations