© 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. 47199
    Prev
    Next
    INDEX
    Explanations

    Wendy's, Five Guys, Raising Cane's, BK

    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
     Shetland
    0.59
     CLP
    0.57
     ম্যানে
    0.57
    mnt
    0.57
     EUR
    0.56
     périph
    0.55
     LSR
    0.55
    mV
    0.55
    م
    0.55
     LRC
    0.54
    POSITIVE LOGITS
    ності
    0.55
    ти
    0.52
     стало
    0.52
     стали
    0.50
     nỗi
    0.48
    чить
    0.47
    ו
    0.47
     sobbing
    0.47
     rigid
    0.46
     acabou
    0.46
    Activations Density 0.000%

    No Known Activations