© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 215223
    Prev
    Next
    INDEX
    Explanations

    technical descriptions, company names, and specific terms

    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_16_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
    falen
    0.52
    ان
    0.50
    tra
    0.49
    M
    0.48
    an
    0.47
    arens
    0.46
    iin
    0.46
    shifted
    0.46
    floxacin
    0.46
    tiles
    0.46
    POSITIVE LOGITS
     เพิ่ม
    0.55
     อาจ
    0.52
     ถ้า
    0.50
     พ
    0.48
     கொடுக்க
    0.48
     แต่
    0.48
     Dallas
    0.48
    Когда
    0.48
     ขั้น
    0.47
     പ്ര
    0.46
    Activations Density 0.000%

    No Known Activations