© 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. 47076
    Prev
    Next
    INDEX
    Explanations

    analyze issues, data, code, contracts

    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
     ।।
    0.57
    ש
    0.57
    شمند
    0.57
    ξη
    0.55
    ད
    0.55
     comed
    0.53
    仼
    0.52
     });
    0.52
     salida
    0.52
     pind
    0.51
    POSITIVE LOGITS
    ociation
    0.61
     Yukawa
    0.61
     scrambling
    0.59
     restarting
    0.59
     ஊக்கு
    0.57
     essentiellement
    0.54
     renewing
    0.54
    Gets
    0.54
     overturning
    0.53
     सोबत
    0.53
    Activations Density 0.008%

    No Known Activations