© 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. 53039
    Prev
    Next
    INDEX
    Explanations

    year 8

    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
    がありました
    0.37
    無理
    0.34
    障害
    0.34
     لديها
    0.33
     never
    0.33
     部
    0.33
    மொ
    0.33
     लॉ
    0.33
    污
    0.32
     sleigh
    0.31
    POSITIVE LOGITS
     moda
    0.41
     relat
    0.39
    лектро
    0.38
     alumna
    0.37
     basename
    0.36
    🌴
    0.36
    ต่
    0.36
     Aper
    0.36
    MAPb
    0.36
     হাইড্রোজেন
    0.36
    Activations Density 0.002%

    No Known Activations