© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 200008
    Prev
    Next
    INDEX
    Explanations

    delegates and events

    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_15_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
    /
    0.63
    德
    0.57
    ě
    0.56
    Ẻ
    0.54
    넬
    0.54
    Ě
    0.53
     carbonyl
    0.53
    стых
    0.53
    ę
    0.53
     bardziej
    0.52
    POSITIVE LOGITS
    ುವುದು
    0.48
    луйста
    0.47
    hma
    0.47
    Correspond
    0.46
     aude
    0.46
    वृत्ति
    0.45
    برا
    0.45
    叁章
    0.45
    ড়ানো
    0.44
    curr
    0.44
    Activations Density 0.001%

    No Known Activations