© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6831
    Prev
    Next
    INDEX
    Explanations

    Japanese and Korean language usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_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
    refrac
    0.47
    駱
    0.45
    vég
    0.45
    contador
    0.45
    lob
    0.44
    trump
    0.44
     saranno
    0.43
    ंपूर्
    0.43
    荊
    0.43
    ých
    0.42
    POSITIVE LOGITS
     좋아
    0.58
     사용할
    0.57
     사용하여
    0.52
     많이
    0.48
     크게
    0.48
     만들어
    0.48
     얻
    0.47
    扱う
    0.47
     받
    0.46
     알려
    0.46
    Activations Density 0.013%

    No Known Activations