© 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. 40749
    Prev
    Next
    INDEX
    Explanations

    internet connection

    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
    لی
    0.69
    mış
    0.65
     bisque
    0.64
    ش
    0.64
    ্যা
    0.63
    عنی
    0.61
    地の
    0.61
    ﺔ
    0.61
    murder
    0.61
     Bisc
    0.60
    POSITIVE LOGITS
    á
    0.55
    ۔
    0.54
     appet
    0.54
     spôsob
    0.54
    é
    0.53
    ov
    0.52
     νέα
    0.52
    í
    0.51
    ви
    0.51
    τή
    0.49
    Activations Density 0.010%

    No Known Activations