© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 153869
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_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
    alibaba
    0.50
    robespierre
    0.49
     Hongkong
    0.47
    怆
    0.46
     kucch
    0.46
    unsplash
    0.46
    ibusdam
    0.46
    UIImage
    0.46
    듑
    0.45
    ッチン
    0.45
    POSITIVE LOGITS
    ↵↵
    0.55
     PC
    0.45
    టకు
    0.43
     和
    0.42
     Lawyers
    0.42
    Grant
    0.42
    OE
    0.42
    Ἁ
    0.41
     oble
    0.41
    ي
    0.41
    Activations Density 0.000%

    No Known Activations