© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 179892
    Prev
    Next
    INDEX
    Explanations

    sketching or graphing concepts

    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_24_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
    綰
    0.41
    駆動
    0.40
    ﹂
    0.38
     বয়সী
    0.37
    다
    0.37
     Photography
    0.36
    ノン
    0.36
    ミー
    0.36
     да
    0.36
    渋
    0.36
    POSITIVE LOGITS
    wara
    0.43
     carreteras
    0.41
     eighteen
    0.41
     barren
    0.41
     formas
    0.40
     ceb
    0.40
    -;
    0.40
     sable
    0.39
    었는데
    0.38
    пом
    0.38
    Activations Density 0.000%

    No Known Activations