© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8532
    Prev
    Next
    INDEX
    Explanations

    JSON structure items

    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_13_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
    جميع
    0.54
     Бүген
    0.52
    꼐
    0.50
     нефте
    0.49
    𝕦
    0.48
     are
    0.47
     هستند
    0.47
    中です
    0.46
    ्टी
    0.46
     всех
    0.46
    POSITIVE LOGITS
    L
    0.61
     –
    0.54
    ojen
    0.49
     dapat
    0.48
     rider
    0.48
     יכול
    0.48
     variability
    0.48
    스와
    0.48
    rades
    0.47
     player
    0.47
    Activations Density 0.028%

    No Known Activations