© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 121399
    Prev
    Next
    INDEX
    Explanations

    war context, items, and plans

    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_3_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
    7
    0.91
     conflict
    0.77
    4
    0.77
     konflikt
    0.74
     conflicts
    0.73
     konflik
    0.71
     Conflicts
    0.71
    Conflict
    0.70
    3
    0.70
    9
    0.70
    POSITIVE LOGITS
    ang
    0.74
    िन
    0.67
    cambrian
    0.64
    ain
    0.63
    im
    0.63
    ia
    0.63
    eed
    0.63
    em
    0.62
    i
    0.62
    it
    0.61
    Activations Density 0.001%

    No Known Activations