© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206522
    Prev
    Next
    INDEX
    Explanations

    write a function

    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_20_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
    f
    0.24
    ім
    0.22
     ስለዚህ
    0.21
    b
    0.21
     변
    0.20
     цих
    0.20
     ім
    0.19
     ф
    0.19
    им
    0.19
    ตั้งแต่
    0.19
    POSITIVE LOGITS
    tee
    0.22
     Ophthalmology
    0.22
     Loco
    0.21
     Palma
    0.21
    𝑰
    0.21
     TSC
    0.21
    篪
    0.21
    arei
    0.21
     विद्यालय
    0.21
    acağım
    0.21
    Activations Density 0.000%

    No Known Activations