© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62765
    Prev
    Next
    INDEX
    Explanations

    proud / pride

    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_11_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
     αυτή
    0.69
     በእ
    0.67
     هذه
    0.64
     ಈ
    0.60
     මෙම
    0.60
    ت
    0.59
    తో
    0.58
    Lr
    0.58
     உருவாக்கி
    0.57
    ޕ
    0.57
    POSITIVE LOGITS
    :
    0.56
     travel
    0.54
    го
    0.53
     inconvenience
    0.53
    ;
    0.53
     buku
    0.48
     tuck
    0.48
    >
    0.47
     mengenai
    0.47
     tribunal
    0.47
    Activations Density 0.001%

    No Known Activations