© 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. 167926
    Prev
    Next
    INDEX
    Explanations

    ),

    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
    emm
    0.43
     पड़े
    0.40
     sencillo
    0.38
     ಗು
    0.37
     присут
    0.37
     оказыва
    0.37
    达到
    0.37
    简单的
    0.37
     doel
    0.36
    "},
    0.36
    POSITIVE LOGITS
    ليا
    0.38
    ربة
    0.37
     delegations
    0.37
    chea
    0.37
     IAEA
    0.37
    helium
    0.36
     Popul
    0.35
     Symbol
    0.35
    ulently
    0.35
     nazionale
    0.34
    Activations Density 0.004%

    No Known Activations