© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7486
    Prev
    Next
    INDEX
    Explanations

    discord bot token

    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_39_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
    chitz
    0.42
     صدر
    0.40
     сервера
    0.40
     Observation
    0.39
     OnInit
    0.38
     waking
    0.37
     ಮಿ
    0.37
     Spinach
    0.37
    পক্ষের
    0.37
    棗
    0.36
    POSITIVE LOGITS
    Kick
    0.44
     franchises
    0.40
    partners
    0.40
    Dis
    0.39
     partners
    0.39
    Partner
    0.39
    ongan
    0.38
     adhesives
    0.38
     franchise
    0.38
    élé
    0.38
    Activations Density 0.013%

    No Known Activations