© 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. 217364
    Prev
    Next
    INDEX
    Explanations

    seen

    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
    Not in Any Lists

    No Comments

    Negative Logits
     thé
    0.42
     roofing
    0.41
    থে
    0.39
    θε
    0.38
     Sow
    0.38
     furnishing
    0.37
     vendor
    0.37
    [(\
    0.36
     thee
    0.36
     rooftop
    0.36
    POSITIVE LOGITS
    aub
    0.41
    ührung
    0.38
    ream
    0.37
    mack
    0.36
    omer
    0.35
    Quran
    0.35
    brit
    0.35
     Qur
    0.35
    greek
    0.35
    ırmaya
    0.34
    Activations Density 0.017%

    No Known Activations