© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37745
    Prev
    Next
    INDEX
    Explanations

    coffee table

    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_11_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
     an
    0.57
    ни
    0.57
     untuk
    0.56
     위한
    0.54
     doubting
    0.54
     C
    0.53
            
    0.52
     par
    0.52
     arthritis
    0.52
    ed
    0.51
    POSITIVE LOGITS
    家里
    0.55
    家の
    0.51
    ớp
    0.51
    getResponseCode
    0.51
    σωπ
    0.50
    家に
    0.50
     নির্মান
    0.49
    霁
    0.48
    ႁ
    0.48
     আর্ক
    0.47
    Activations Density 0.007%

    No Known Activations