© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 62991
    Prev
    Next
    INDEX
    Explanations

    Rupert Murdoch

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     kill
    0.61
     killing
    0.54
    Killing
    0.50
     уби
    0.48
    killing
    0.48
     killed
    0.48
     KILL
    0.48
     Killing
    0.46
    killed
    0.46
    殺
    0.46
    POSITIVE LOGITS
     Rupert
    0.77
    Ru
    0.74
     ru
    0.71
     Ru
    0.71
     RU
    0.62
    RU
    0.60
     Ruiz
    0.57
     Murdoch
    0.54
    ru
    0.51
    Ruf
    0.51
    Activations Density 0.003%

    No Known Activations