© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 30831
    Prev
    Next
    INDEX
    Explanations

    so

    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_50_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
    urst
    0.48
    ۇر
    0.46
    uros
    0.45
    KUR
    0.45
    urón
    0.45
    urat
    0.45
     chorus
    0.43
     kur
    0.42
    濂
    0.42
    ured
    0.41
    POSITIVE LOGITS
    olo
    0.59
     ul
    0.57
    cul
    0.56
     Ul
    0.55
    Ul
    0.54
    OLO
    0.54
     cul
    0.53
    울
    0.52
    UL
    0.51
    Kul
    0.50
    Activations Density 0.010%

    No Known Activations