© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 79722
    Prev
    Next
    INDEX
    Explanations

    Context

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
     karn
    0.40
     క్యా
    0.39
     cub
    0.39
    ieb
    0.38
    郎
    0.37
     الجم
    0.36
    桌面
    0.36
     Tote
    0.35
    貓
    0.35
     डिवीजन
    0.35
    POSITIVE LOGITS
     Context
    1.30
     Кон
    1.30
    Кон
    1.25
    Context
    1.21
     कॉन्
    1.21
     контек
    1.16
    コン
    1.13
     context
    1.13
    context
    1.13
     컨
    1.12
    Activations Density 0.002%

    No Known Activations