© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14541
    Prev
    Next
    INDEX
    Explanations

    Bundle

    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_15_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
    ेशन
    0.49
     çalışmaları
    0.48
     സൂര്യ
    0.48
    银
    0.48
    方向
    0.48
    ర్‌
    0.48
    劻
    0.47
    ल्ल्या
    0.47
     methyl
    0.46
     доставка
    0.46
    POSITIVE LOGITS
    מ
    0.55
    ค
    0.54
    و
    0.51
    וא
    0.51
    ב
    0.48
    ij
    0.47
    including
    0.47
    וג
    0.47
    nacht
    0.46
    fm
    0.46
    Activations Density 0.001%

    No Known Activations