© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 205533
    Prev
    Next
    INDEX
    Explanations

    assassinations and political figures

    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_20_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
    characteristic
    0.42
    intu
    0.41
    integration
    0.40
    ☘
    0.40
    (["
    0.39
    テック
    0.39
     કરવાની
    0.39
     humo
    0.39
    ()[
    0.38
    ome
    0.38
    POSITIVE LOGITS
     ALLOYS
    0.45
    ੁੱ
    0.44
     FabD
    0.43
     ഏറ്റ
    0.42
    apd
    0.41
     memorial
    0.40
     tasked
    0.40
     beaded
    0.39
     crumbled
    0.39
     snout
    0.39
    Activations Density 0.000%

    No Known Activations