© 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. 227442
    Prev
    Next
    INDEX
    Explanations

    standard

    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
    s
    1.10
    \
    1.04
    ים
    0.90
    </h2>
    0.90
     costume
    0.89
     l
    0.88
     oblik
    0.86
    <0x0D>
    0.83
    アート
    0.80
    はじめ
    0.79
    POSITIVE LOGITS
    as
    1.15
    on
    1.12
    ت
    1.10
    ل
    1.09
    et
    1.05
    其他
    0.96
    ب
    0.89
    ن
    0.89
    و
    0.88
    ান
    0.87
    Activations Density 0.003%

    No Known Activations