© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210347
    Prev
    Next
    INDEX
    Explanations

    Горного Алтая

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_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
    ابقات
    0.49
    circledR
    0.46
     Río
    0.44
    股份
    0.44
    ₲
    0.44
    ᴿ
    0.43
    Ꮃ
    0.43
    푅
    0.42
    可能的
    0.41
    ugeot
    0.41
    POSITIVE LOGITS
     uten
    0.44
     Бере
    0.43
     quant
    0.39
    quan
    0.39
     END
    0.38
    おか
    0.38
    ля
    0.38
     tanpa
    0.38
    Without
    0.38
     dec
    0.38
    Activations Density 0.001%

    No Known Activations