© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18148
    Prev
    Next
    INDEX
    Explanations

    enhancement, Policy, Gradient

    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_15_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
     سی
    0.40
    ێر
    0.37
     بۆ
    0.36
     quirks
    0.36
    !"
    0.35
     inégal
    0.35
     ユ
    0.34
    Inflation
    0.34
     মানবাধিকার
    0.34
     pipes
    0.34
    POSITIVE LOGITS
     Mahar
    0.41
     potente
    0.41
    Пер
    0.40
    ụ
    0.40
     Mahatma
    0.40
    さら
    0.39
     Tendulkar
    0.39
     Lecturer
    0.39
    चना
    0.38
     ઉ
    0.38
    Activations Density 0.065%

    No Known Activations