© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 236478
    Prev
    Next
    INDEX
    Explanations

    LaTeX drawing commands

    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_32_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
    পোর্ট
    0.42
    дата
    0.40
    Mex
    0.39
    گیرد
    0.38
    รับ
    0.38
     Règ
    0.38
     Gue
    0.36
    妵
    0.36
    الحضور
    0.36
     கும்ப
    0.36
    POSITIVE LOGITS
     uphill
    0.40
     nominee
    0.37
     اک
    0.37
     තම
    0.36
     currentPlayer
    0.36
     travelling
    0.35
    ('.
    0.34
     τελευτα
    0.33
     क्लासेस
    0.33
     dalamnya
    0.33
    Activations Density 0.000%

    No Known Activations