© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13800
    Prev
    Next
    INDEX
    Explanations

    convex geometry and optimization

    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_13_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
    )*
    0.17
    *;
    0.17
    Neurons
    0.16
    dr
    0.15
    tr
    0.15
    ;
    0.15
    Largest
    0.15
    lineContainer
    0.15
    西哥
    0.15
    راتكم
    0.15
    POSITIVE LOGITS
    ไม
    0.17
    茗
    0.17
    みの
    0.17
     Q
    0.16
     MI
    0.15
     Yangzhou
    0.15
    เสนอ
    0.15
    ംഗ്
    0.15
     Xiao
    0.15
     Yue
    0.15
    Activations Density 0.002%

    No Known Activations