© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 155639
    Prev
    Next
    INDEX
    Explanations

    r

    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_60_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
    える
    0.92
    ਾ
    0.68
    ів
    0.65
    os
    0.61
    oc
    0.61
    ოში
    0.61
    ز
    0.60
    وك
    0.59
    وڈ
    0.59
    oč
    0.59
    POSITIVE LOGITS
    re
    0.47
    new
    0.47
     Out
    0.42
    rese
    0.42
     Up
    0.42
    wens
    0.41
    tris
    0.41
     CHANGE
    0.41
     CHARACTER
    0.41
    had
    0.40
    Activations Density 0.000%

    No Known Activations