© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 215270
    Prev
    Next
    INDEX
    Explanations

    the letter Я

    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
    ovne
    0.42
     QUEEN
    0.40
     व्यू
    0.39
    繆
    0.39
    անի
    0.38
    می
    0.38
     prophe
    0.38
     വിവാ
    0.37
     Queen
    0.37
     Zor
    0.37
    POSITIVE LOGITS
     Я
    1.01
     Ya
    0.95
     я
    0.92
     야
    0.83
    Ya
    0.80
     ya
    0.80
    ヤ
    0.78
     YA
    0.77
     ヤ
    0.77
     Yah
    0.73
    Activations Density 0.001%

    No Known Activations