© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 79452
    Prev
    Next
    INDEX
    Explanations

    ky kỳ

    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_53_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
    C
    0.43
    الص
    0.41
     C
    0.40
    Caut
    0.38
     каза
    0.38
     شناخت
    0.37
     vòng
    0.36
     सी
    0.36
     ஆ
    0.35
    mandu
    0.35
    POSITIVE LOGITS
     ky
    0.79
     kỳ
    0.77
     Ky
    0.76
    Ky
    0.74
     Kỳ
    0.74
     kì
    0.70
    ky
    0.61
    Kyle
    0.59
     Kyle
    0.58
     KY
    0.55
    Activations Density 0.000%

    No Known Activations