© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57815
    Prev
    Next
    INDEX
    Explanations

    Korean particles

    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_59_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
     d
    1.11
     د
    1.02
     д
    0.89
     द
    0.77
     ד
    0.73
     ద
    0.65
     দ
    0.65
     દ
    0.58
     ਦ
    0.57
     դ
    0.50
    POSITIVE LOGITS
     가
    0.98
    가
    0.65
    ГА
    0.63
    은
    0.61
    는
    0.59
     га
    0.58
    Ga
    0.56
    هم
    0.55
    ها
    0.54
    도
    0.53
    Activations Density 0.000%

    No Known Activations