© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 92911
    Prev
    Next
    INDEX
    Explanations

    multilingual AI responses

    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_60_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
     си
    3.13
     Си
    2.80
     सि
    2.52
    シ
    2.52
    Си
    2.50
     السي
    2.36
     سي
    2.31
     سی
    2.31
     Sí
    2.31
     סי
    2.27
    POSITIVE LOGITS
     ICE
    0.37
     GTEST
    0.32
    ษฐ
    0.32
    ermes
    0.31
     Gough
    0.31
     quench
    0.31
    昉
    0.29
    㕝
    0.29
    戴
    0.29
    涿
    0.29
    Activations Density 0.041%

    No Known Activations