© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17602
    Prev
    Next
    INDEX
    Explanations

    XP, points, tournament results

    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_34_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
    相關文章
    0.42
     අය
    0.39
    WithName
    0.38
    ដៃ
    0.38
     Suites
    0.37
     кере
    0.36
    クリー
    0.36
    㡺
    0.35
     suite
    0.35
    suite
    0.34
    POSITIVE LOGITS
    Large
    0.44
     Punkte
    0.41
    large
    0.39
     Negara
    0.39
     actividad
    0.38
     Estado
    0.38
     liquide
    0.38
    unkte
    0.38
     Valuable
    0.38
     estamos
    0.37
    Activations Density 0.004%

    No Known Activations