© 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. 207663
    Prev
    Next
    INDEX
    Explanations

    the

    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
    Negative Logits
     worse
    0.56
     worst
    0.53
     Presidents
    0.43
     toe
    0.42
     Worst
    0.41
     only
    0.40
     Worse
    0.40
     improvement
    0.40
    沉
    0.40
    worst
    0.39
    POSITIVE LOGITS
    Mer
    0.45
    Supply
    0.44
     mer
    0.43
     mers
    0.40
    Bracket
    0.39
    ុម
    0.39
    getMain
    0.38
    smt
    0.38
     المر
    0.38
     عالية
    0.38
    Activations Density 0.000%

    No Known Activations