© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 142311
    Prev
    Next
    INDEX
    Explanations

    energy, time, physical processes

    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_12_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
    抔
    0.44
     jours
    0.44
     بہانہ
    0.44
     Rohr
    0.43
    संख्य
    0.43
     неболь
    0.42
     répand
    0.42
    nsec
    0.42
    ято
    0.42
    بلا
    0.42
    POSITIVE LOGITS
     in
    0.46
     distinctly
    0.41
     ”
    0.41
     Particularly
    0.39
    olom
    0.38
     with
    0.38
     lev
    0.37
     produk
    0.37
     ট
    0.36
    誡
    0.36
    Activations Density 0.004%

    No Known Activations