© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 131529
    Prev
    Next
    INDEX
    Explanations

    say "way"

    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
     IQR
    0.41
     कैन
    0.37
    澈
    0.36
    odrome
    0.36
    jezd
    0.36
     رفض
    0.36
     jeb
    0.35
    olda
    0.35
     اقسام
    0.35
    বেদ
    0.35
    POSITIVE LOGITS
    긴
    0.40
     thing
    0.38
     লে
    0.37
     Hun
    0.35
     Rec
    0.35
    allus
    0.35
     উপযোগী
    0.35
     prefers
    0.34
    기는
    0.34
    affirm
    0.34
    Activations Density 0.002%

    No Known Activations