© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 135051
    Prev
    Next
    INDEX
    Explanations

    architecture

    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_6_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
    ด
    0.77
    ב
    0.74
    ל
    0.71
    ä
    0.70
    리
    0.69
    at
    0.66
    त
    0.66
    For
    0.66
    า
    0.65
    ü
    0.65
    POSITIVE LOGITS
     коне
    0.60
     ﺍﻟ
    0.58
     كون
    0.58
     అందించ
    0.58
     площа
    0.57
     خلي
    0.55
     щи
    0.55
     мод
    0.55
     Фе
    0.54
    _
    0.54
    Activations Density 0.003%

    No Known Activations