© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62743
    Prev
    Next
    INDEX
    Explanations

    longer lasting

    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_11_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
     protracted
    0.57
    Tiempo
    0.56
    นาน
    0.55
    镤
    0.55
    OST
    0.54
     posibil
    0.52
    久的
    0.52
     طويلة
    0.52
    आउट
    0.52
     طويل
    0.52
    POSITIVE LOGITS
    ffer
    0.59
    to
    0.53
    2
    0.52
     to
    0.52
    ip
    0.51
    ave
    0.49
     Excited
    0.49
    0
    0.49
     soothe
    0.48
    }{
    0.46
    Activations Density 0.014%

    No Known Activations