© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 199596
    Prev
    Next
    INDEX
    Explanations

    the letter K

    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
     पो
    0.39
    苙
    0.38
    託
    0.37
     Newport
    0.37
     biomedical
    0.36
    ieke
    0.36
    मिटेड
    0.36
     социальной
    0.35
     Владимир
    0.35
     Camel
    0.35
    POSITIVE LOGITS
     K
    1.55
    K
    1.16
     К
    1.05
     الك
    1.05
     ک
    1.00
    k
    0.90
     k
    0.84
    Ｋ
    0.84
     ক
    0.84
     Κ
    0.84
    Activations Density 0.007%

    No Known Activations