© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 236839
    Prev
    Next
    INDEX
    Explanations

    function arguments

    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_32_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
    lera
    0.39
    橇
    0.39
     logrado
    0.38
    nice
    0.37
    চাই
    0.36
     पढ़ेंः
    0.36
    ások
    0.35
    రావు
    0.35
     நடித்த
    0.34
    팅
    0.34
    POSITIVE LOGITS
     ကု
    0.37
     Kuznet
    0.36
    Married
    0.36
    èvement
    0.36
     दिवा
    0.36
    孀
    0.36
    の使い方
    0.35
     Married
    0.35
     ابن
    0.35
     adversaries
    0.35
    Activations Density 0.003%

    No Known Activations