© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46160
    Prev
    Next
    INDEX
    Explanations

    school, orders, climax

    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
    า
    0.79
    ت
    0.76
    د
    0.75
    ง
    0.74
    ش
    0.73
    त
    0.67
    ه
    0.66
    기
    0.63
    م
    0.63
    ف
    0.62
    POSITIVE LOGITS
    \})
    0.64
    ças
    0.57
    btnAdd
    0.52
    轢
    0.52
    。<
    0.51
     fouls
    0.51
    ږئ
    0.50
    tAux
    0.50
     μικ
    0.49
     оке
    0.49
    Activations Density 0.000%

    No Known Activations