© 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. 41232
    Prev
    Next
    INDEX
    Explanations

    Menlo Park, Iran, Waverley

    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
    i
    0.66
    ↵
    0.62
    -
    0.55
    or
    0.53
    is
    0.49
     हात
    0.49
    er
    0.49
    has
    0.49
    etern
    0.48
    ل
    0.47
    POSITIVE LOGITS
     requerido
    0.70
    लेकिन
    0.56
    тео
    0.55
     अर्चना
    0.54
     argentinos
    0.52
    рованный
    0.51
     przez
    0.51
     станет
    0.51
    ্সা
    0.51
     pudieran
    0.51
    Activations Density 0.000%

    No Known Activations