© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206196
    Prev
    Next
    INDEX
    Explanations

    logging level

    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_20_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
    design
    0.48
    ออกแบบ
    0.48
    ann
    0.47
    visits
    0.45
    วิ
    0.44
    videos
    0.44
    ็
    0.43
     videos
    0.43
    new
    0.42
    ups
    0.42
    POSITIVE LOGITS
    ﹁
    0.48
    ﻕ
    0.47
    륙
    0.46
    +#+#+
    0.46
     controlar
    0.46
    épid
    0.45
     sylvis
    0.44
     resaltar
    0.44
    ⌔
    0.44
    Todas
    0.44
    Activations Density 0.001%

    No Known Activations