© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 201043
    Prev
    Next
    INDEX
    Explanations

    military units

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     অভিষ
    0.43
    oes
    0.41
    chy
    0.38
    வண
    0.38
     Cheval
    0.37
    בור
    0.37
    ণ্ডল
    0.36
    ㄚ
    0.36
    म्र
    0.36
    abis
    0.36
    POSITIVE LOGITS
     detachment
    2.05
     detach
    1.94
    detach
    1.70
     detached
    1.60
    Detach
    1.59
     Det
    1.50
    detached
    1.47
    Det
    1.34
     détach
    1.32
     dét
    1.23
    Activations Density 0.001%

    No Known Activations