© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 226583
    Prev
    Next
    INDEX
    Explanations

    maritime laws, safety, and shipping

    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_10_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
     atractivo
    0.75
    as
    0.72
     ~$
    0.58
     integrate
    0.57
    indruck
    0.57
     pię
    0.57
     odio
    0.57
     বৈদ্য
    0.57
     языке
    0.56
     $
    0.55
    POSITIVE LOGITS
     maritime
    0.96
    Maritime
    0.89
    g
    0.89
     Maritime
    0.86
    船
    0.81
     t
    0.77
     marine
    0.74
    船舶
    0.70
     nautical
    0.66
     Marine
    0.65
    Activations Density 0.009%

    No Known Activations