© 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. 1171
    Prev
    Next
    INDEX
    Explanations

    law enforcement and security officers

    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
     डिफेंस
    0.38
    BBB
    0.38
    铡
    0.38
    BSC
    0.37
    詓
    0.37
     Alison
    0.37
     বিজ্ঞাপন
    0.37
    ጻ
    0.36
     менедж
    0.36
     लड़
    0.35
    POSITIVE LOGITS
     deployment
    0.67
     deployed
    0.63
     forces
    0.63
     deployments
    0.62
     forze
    0.61
     officers
    0.61
     Forces
    0.60
     deploying
    0.59
     মোতায়
    0.59
     Deployment
    0.58
    Activations Density 0.070%

    No Known Activations