© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13289
    Prev
    Next
    INDEX
    Explanations

    World Trade Center collapse thermite

    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_15_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    面临
    0.46
    awing
    0.45
    а
    0.44
    или
    0.44
    ма
    0.44
    шта
    0.44
    ائو
    0.43
    Bismillahirrah
    0.43
    тый
    0.42
    є
    0.42
    POSITIVE LOGITS
     penyeleng
    0.55
     messageFields
    0.53
    oluminescence
    0.53
     acceptor
    0.52
    淒
    0.52
    OD
    0.52
     przem
    0.52
     дочери
    0.52
     ktorá
    0.51
     xhrObj
    0.50
    Activations Density 0.001%

    No Known Activations