© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14801
    Prev
    Next
    INDEX
    Explanations

    Woodrow Wilson US absence

    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_13_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
     ligação
    0.57
     开发
    0.50
    abileceğ
    0.49
     BAS
    0.48
    مبر
    0.48
     gerenci
    0.48
    䂘
    0.48
    ಳಿತ
    0.46
     BLOG
    0.46
    𝙡
    0.46
    POSITIVE LOGITS
    Rice
    0.50
    queous
    0.43
    Emmanuel
    0.43
    cul
    0.42
    Chip
    0.42
    Clamp
    0.41
    /
    0.41
    гать
    0.40
    itty
    0.40
    ără
    0.40
    Activations Density 0.011%

    No Known Activations