© 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. 13398
    Prev
    Next
    INDEX
    Explanations

    INDEX

    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
     brushing
    0.53
     chewing
    0.51
    estream
    0.51
    T
    0.51
     stumbled
    0.50
    horse
    0.49
     resigned
    0.49
    picking
    0.49
     इस्तीफा
    0.49
     attracting
    0.49
    POSITIVE LOGITS
    ⌵
    0.63
    ارى
    0.61
    으로부터
    0.57
     Zeits
    0.55
    اد
    0.53
     нуля
    0.53
     Sorrent
    0.52
    Ꮩ
    0.52
     SONS
    0.52
     Eind
    0.52
    Activations Density 0.001%

    No Known Activations