© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199956
    Prev
    Next
    INDEX
    Explanations

    massacre, fire, attack, disaster, event

    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_27_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
    ੂ
    0.46
     infr
    0.45
     detractors
    0.41
     actes
    0.41
     disputes
    0.40
    ੈਂ
    0.40
    zeichnung
    0.38
     uden
    0.38
     predictions
    0.37
     forecasts
    0.37
    POSITIVE LOGITS
     Calibri
    0.39
    鳄
    0.36
     вдох
    0.36
     Darn
    0.36
     Channel
    0.36
     Gr
    0.35
     Raid
    0.35
     살펴
    0.34
     Dinosaur
    0.34
     Yunan
    0.34
    Activations Density 0.003%

    No Known Activations