© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 19262
    Prev
    Next
    INDEX
    Explanations

    nuclear weapons and disasters

    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_40_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
    ഘ
    0.41
     scratch
    0.40
    च्यू
    0.39
    ॉल
    0.38
     Qf
    0.38
    قا
    0.38
    గే
    0.37
    ᱼ
    0.37
     Solic
    0.37
    癢
    0.37
    POSITIVE LOGITS
     Fukushima
    1.11
     Hiroshima
    1.06
     nuclear
    1.00
     Nagasaki
    0.96
     Chernobyl
    0.95
    Nuclear
    0.94
     Nuclear
    0.91
    nuclear
    0.88
     NUCLEAR
    0.84
    NUCLEAR
    0.84
    Activations Density 0.051%

    No Known Activations