© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 130056
    Prev
    Next
    INDEX
    Explanations

    say "many" or "Search"

    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
    虎
    0.45
     rad
    0.42
    Async
    0.40
    杯
    0.39
    Rad
    0.39
    KQ
    0.38
    㽛
    0.37
    ρακ
    0.36
     ग्
    0.36
    构造
    0.35
    POSITIVE LOGITS
     Relig
    0.42
     Montgomery
    0.42
     Vali
    0.40
    Montgomery
    0.39
    娅
    0.38
    เวล
    0.38
    ੭
    0.38
     Laur
    0.37
    urte
    0.37
     Mink
    0.36
    Activations Density 0.001%

    No Known Activations