© 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. 35913
    Prev
    Next
    INDEX
    Explanations

    sk word beginnings

    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
     അട
    0.47
     révé
    0.43
    ಙ
    0.41
     crema
    0.39
     nath
    0.38
    anka
    0.37
    angun
    0.37
     পেশ
    0.37
    拙
    0.37
     rivel
    0.36
    POSITIVE LOGITS
    ска
    0.96
    sk
    0.86
    스크
    0.83
    ски
    0.78
    сну
    0.76
    ск
    0.75
    ску
    0.74
    Sk
    0.73
    Ска
    0.71
    סק
    0.70
    Activations Density 0.003%

    No Known Activations