© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33285
    Prev
    Next
    INDEX
    Explanations

    load_data(

    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_3_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
     prób
    0.57
    IA
    0.57
    .
    0.56
    和他
    0.55
     been
    0.54
    UD
    0.54
    load
    0.52
    ┈┈
    0.52
     i
    0.52
    gall
    0.52
    POSITIVE LOGITS
    "
    0.88
    ”
    0.64
    ol
    0.57
    కి
    0.57
    ل
    0.57
    ى
    0.57
     cigar
    0.56
    il
    0.55
    ка
    0.54
    व
    0.54
    Activations Density 0.007%

    No Known Activations