© 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. 226980
    Prev
    Next
    INDEX
    Explanations

    Netherlands

    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
    م
    1.20
    UM
    1.06
     for
    1.03
    ني
    1.02
    ENA
    1.01
     is
    0.96
    تي
    0.96
    ore
    0.95
    EN
    0.93
    تين
    0.92
    POSITIVE LOGITS
    x
    1.20
    ב
    1.10
    も
    1.03
    도
    1.00
    เรา
    0.91
    αν
    0.90
    ᱐
    0.90
    ール
    0.89
     Иң
    0.89
    ᱑
    0.89
    Activations Density 0.001%

    No Known Activations