© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102771
    Prev
    Next
    INDEX
    Explanations

    boat or barge types

    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_14_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
    マン
    0.59
    im
    0.57
     विश्वविद्यालयों
    0.55
    am
    0.52
    é
    0.50
    learned
    0.50
    agangan
    0.50
    vat
    0.50
    Բ
    0.50
    vl
    0.49
    POSITIVE LOGITS
     caravan
    0.57
     pequeña
    0.57
     loaves
    0.55
     barges
    0.52
     وسائل
    0.52
     pequena
    0.51
     barge
    0.51
    到
    0.50
     связи
    0.49
     barric
    0.49
    Activations Density 0.000%

    No Known Activations