© 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. 170471
    Prev
    Next
    INDEX
    Explanations

    peaceful nuclear energy, resolution, or reunification

    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
     świata
    0.43
    ukawa
    0.42
    Photon
    0.42
    阅
    0.42
    酞
    0.41
     العالم
    0.41
     photons
    0.41
     текста
    0.41
    atangan
    0.40
    文書
    0.39
    POSITIVE LOGITS
    嫉
    0.50
     lequel
    0.48
     selon
    0.47
     которого
    0.47
     Elinor
    0.46
     feasible
    0.46
     atrav
    0.46
     Klopp
    0.44
     stomp
    0.44
     laquelle
    0.43
    Activations Density 0.000%

    No Known Activations