© 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. 215691
    Prev
    Next
    INDEX
    Explanations

    South Korea

    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
     사전
    0.39
    뷸
    0.38
     TK
    0.37
     TBS
    0.37
    ⁡</
    0.37
    felter
    0.37
    ốt
    0.37
     KBS
    0.37
    igu
    0.36
     onc
    0.36
    POSITIVE LOGITS
    PES
    0.49
    UP
    0.42
    P
    0.39
    রাতে
    0.38
    완
    0.38
     Mares
    0.38
     inmig
    0.37
    PER
    0.37
     peste
    0.37
     P
    0.36
    Activations Density 0.009%

    No Known Activations