© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89992
    Prev
    Next
    INDEX
    Explanations

    buildings and infrastructure damage

    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_23_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
    费用
    0.44
    emand
    0.42
    යන්
    0.40
     चेतावनी
    0.39
    adan
    0.38
     कागज
    0.38
    满
    0.38
    简称
    0.38
    юд
    0.38
    每月
    0.38
    POSITIVE LOGITS
     sexta
    0.44
    transmitter
    0.40
     QFile
    0.40
     Goode
    0.39
    監
    0.38
     crumb
    0.38
     Nepal
    0.38
     terceiro
    0.38
    aptic
    0.37
     sétimo
    0.37
    Activations Density 0.006%

    No Known Activations