© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 241374
    Prev
    Next
    INDEX
    Explanations

    learning new things

    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_40_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
     něco
    0.39
     coś
    0.38
     Something
    0.37
     例
    0.37
    something
    0.37
     imen
    0.36
     Moody
    0.36
     হোল
    0.36
     alfabet
    0.35
     qualcosa
    0.35
    POSITIVE LOGITS
     new
    0.52
     نئے
    0.45
     नए
    0.43
     новую
    0.41
     नये
    0.41
    new
    0.40
    新しい
    0.39
    疇
    0.38
     новых
    0.38
     Brunch
    0.38
    Activations Density 0.006%

    No Known Activations