© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2013
    Prev
    Next
    INDEX
    Explanations

    at the end

    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_40_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
    Arc
    0.41
    arc
    0.40
     בצ
    0.38
    ARC
    0.37
     באתר
    0.37
     Arc
    0.36
    ERICA
    0.36
    㞔
    0.36
    Chapter
    0.36
    ளைஞ
    0.36
    POSITIVE LOGITS
     끝
    0.65
     end
    0.60
    끝
    0.57
     конца
    0.47
    end
    0.46
     শেষ
    0.44
    olinha
    0.42
     конце
    0.41
    スケジュール
    0.40
     до
    0.40
    Activations Density 0.053%

    No Known Activations