© 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. 212879
    Prev
    Next
    INDEX
    Explanations

    upside

    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
     W
    0.43
     tue
    0.38
     subjects
    0.34
    ng
    0.34
    カン
    0.34
     preferences
    0.33
     ከመ
    0.33
    unitas
    0.33
    ¬
    0.32
     fant
    0.32
    POSITIVE LOGITS
    Rum
    0.41
     enlev
    0.41
     rum
    0.41
     Enrico
    0.41
    garage
    0.41
     Rum
    0.40
    rvGroup
    0.40
    Yard
    0.40
    Zd
    0.39
     Ennis
    0.39
    Activations Density 0.000%

    No Known Activations