© 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. 45573
    Prev
    Next
    INDEX
    Explanations

    pull-up resistors

    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
     عبدالع
    0.62
    廛
    0.58
     erreurs
    0.58
     سپورت
    0.57
     mogą
    0.54
     кеңсе
    0.54
    পিং
    0.54
    سال
    0.54
    스를
    0.54
     سیستم
    0.54
    POSITIVE LOGITS
     It
    0.61
     p
    0.59
     m
    0.55
     hand
    0.55
     me
    0.54
    0.52
    rist
    0.52
    orski
    0.51
     Mr
    0.51
     K
    0.50
    Activations Density 0.012%

    No Known Activations