© 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. 47977
    Prev
    Next
    INDEX
    Explanations

    before making

    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
     לפני
    0.36
    モード
    0.34
    ‌ترین
    0.34
     before
    0.33
     Rodríguez
    0.33
     prije
    0.33
    旷
    0.33
     レン
    0.32
     lordship
    0.32
     dene
    0.32
    POSITIVE LOGITS
    क्रीम
    0.40
     накопи
    0.39
     inventing
    0.39
     crus
    0.37
    jec
    0.37
     Crusade
    0.37
    >');
    0.36
    ធាតុ
    0.36
     Primer
    0.36
    }');
    0.36
    Activations Density 0.000%

    No Known Activations