© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5400
    Prev
    Next
    INDEX
    Explanations

    standing army

    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
     Marxist
    0.57
     URANIUM
    0.52
     инициа
    0.52
    秕
    0.51
     UNNEEDED
    0.50
     இரண்டாம்
    0.49
     বিরাট
    0.49
     jeweils
    0.48
     NICKEL
    0.48
    㼛
    0.48
    POSITIVE LOGITS
    াদিগের
    0.58
     exertions
    0.57
     effectual
    0.54
     voitures
    0.54
     commence
    0.53
    ∣
    0.53
     principles
    0.52
     commenced
    0.52
     countenance
    0.52
     melancholy
    0.52
    Activations Density 0.020%

    No Known Activations