© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30992
    Prev
    Next
    INDEX
    Explanations

    questions and instructions for actions

    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_31_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
    zia
    0.38
     Techniques
    0.36
    এক
    0.35
     ㄴ
    0.35
    ㄱ
    0.35
    ៩
    0.34
     बिलकुल
    0.34
     સ્વા
    0.34
     কানে
    0.34
    কিন্তু
    0.34
    POSITIVE LOGITS
    FileType
    0.39
    什么样的
    0.38
     encuentre
    0.37
     apakah
    0.37
     Apakah
    0.36
    是否有
    0.36
     jaką
    0.36
    是否
    0.35
     هل
    0.35
    伏
    0.35
    Activations Density 0.003%

    No Known Activations