© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 68754
    Prev
    Next
    INDEX
    Explanations

    korean words

    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_46_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
     Кита
    0.46
     /$
    0.40
     Mamata
    0.40
    اوى
    0.39
    INDIA
    0.39
    璨
    0.38
    ígen
    0.38
    Pemb
    0.38
    ücklich
    0.38
     китай
    0.38
    POSITIVE LOGITS
    cheon
    0.57
    천
    0.56
     천
    0.55
    天
    0.50
     Chun
    0.49
     Chung
    0.46
    忠
    0.43
     부여
    0.42
     sky
    0.41
     enshrined
    0.41
    Activations Density 0.001%

    No Known Activations