© 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. 136355
    Prev
    Next
    INDEX
    Explanations

    Buffer serialization

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ê
    0.55
    p
    0.54
    ா
    0.52
    屻
    0.52
     curvature
    0.51
     suscept
    0.50
    벤트
    0.50
    ę
    0.49
     vento
    0.49
     comfortably
    0.48
    POSITIVE LOGITS
     بعد
    0.53
     Володимир
    0.51
     Интере
    0.51
     informer
    0.50
     ISNI
    0.50
     hicimos
    0.49
    genetic
    0.49
     Име
    0.48
     मिळत
    0.48
    genome
    0.47
    Activations Density 0.000%

    No Known Activations