© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1170
    Prev
    Next
    INDEX
    Explanations

    negotiated settlement, diplomacy, arms control

    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_39_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ক্ষুধ
    0.39
    ellung
    0.38
    战
    0.37
    Conflicts
    0.36
    Cherry
    0.36
    Factories
    0.36
    రిత్ర
    0.35
     stronghold
    0.35
    Ongoing
    0.35
    Supported
    0.35
    POSITIVE LOGITS
     perceptions
    0.42
     Wiki
    0.41
     brink
    0.40
     美
    0.40
     irrit
    0.39
     Pran
    0.39
    ACTER
    0.39
    apura
    0.39
     spoiler
    0.38
     atmosph
    0.37
    Activations Density 0.032%

    No Known Activations