© 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. 49852
    Prev
    Next
    INDEX
    Explanations

    Kubernetes Deployment

    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
     థ
    0.39
     exploration
    0.39
     knn
    0.38
     Exploration
    0.37
     caloric
    0.37
     هون
    0.36
    ,}$
    0.36
     calorie
    0.36
     폴
    0.36
     Wrestle
    0.36
    POSITIVE LOGITS
     Kubernetes
    0.40
    保护
    0.39
     graf
    0.38
    差
    0.37
     controllers
    0.37
    停止
    0.37
    Badge
    0.36
     অঙ্ক
    0.36
    航
    0.36
    刷
    0.36
    Activations Density 0.019%

    No Known Activations