© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50266
    Prev
    Next
    INDEX
    Explanations

    surgical instructions

    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_31_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
     linkage
    0.39
     clotting
    0.39
    PBS
    0.38
     維
    0.37
     చేస్త
    0.35
     ض
    0.35
    当天
    0.34
     жи
    0.34
    )]$
    0.34
     tenuous
    0.34
    POSITIVE LOGITS
     ആരാധ
    0.42
     Moder
    0.41
     Ray
    0.39
     Hines
    0.38
     mouse
    0.38
    DOMAIN
    0.38
    eyen
    0.38
    員の
    0.38
    二年
    0.38
     uncoated
    0.37
    Activations Density 0.047%

    No Known Activations