© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63293
    Prev
    Next
    INDEX
    Explanations

    you

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fix
    0.47
    fix
    0.45
     Fix
    0.43
     arrivée
    0.41
     broken
    0.41
     된
    0.41
     arrivals
    0.40
     fixer
    0.38
    Fix
    0.38
    arrivals
    0.38
    POSITIVE LOGITS
     অভিজ্ঞ
    0.41
    পিন
    0.41
    NOTICE
    0.41
     체험
    0.41
    UseDebug
    0.41
     বিশ্লেষণের
    0.39
    *>(
    0.39
    ZQ
    0.39
    exper
    0.38
     discovers
    0.38
    Activations Density 0.005%

    No Known Activations