© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171363
    Prev
    Next
    INDEX
    Explanations

    military troops deployed

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Permanent
    0.47
     latitudine
    0.44
     Atmosphere
    0.43
    体
    0.43
     lightweight
    0.42
     Lightweight
    0.42
     Wheaton
    0.41
     evapor
    0.41
     Lat
    0.41
     posterity
    0.41
    POSITIVE LOGITS
    έν
    0.55
    ਾਬ
    0.45
    abhäng
    0.43
     блю
    0.43
     menú
    0.42
    zzel
    0.42
    ショー
    0.41
    늬
    0.41
     enforced
    0.41
    ರ್
    0.41
    Activations Density 0.000%

    No Known Activations