© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 49619
    Prev
    Next
    INDEX
    Explanations

    laws in your area

    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_10_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
    ര
    0.34
    uu
    0.30
    ங்கள்
    0.29
    aru
    0.29
    uuuu
    0.29
    тся
    0.29
     =)
    0.29
    =\
    0.29
    ્ર
    0.28
    йте
    0.28
    POSITIVE LOGITS
    设计
    0.33
    多
    0.29
    ﺒ
    0.29
    Os
    0.28
    b
    0.28
    ৫
    0.27
    大
    0.27
    Р
    0.27
    服务
    0.27
    风
    0.27
    Activations Density 0.010%

    No Known Activations