© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 103269
    Prev
    Next
    INDEX
    Explanations

    lists categorized by specific words

    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_16_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
    וס
    0.52
    و
    0.51
    牴
    0.49
     rédaction
    0.48
    ვის
    0.48
     Horm
    0.47
     hormone
    0.47
    horns
    0.47
     caractère
    0.45
     soup
    0.45
    POSITIVE LOGITS
     OCPP
    0.52
    fitrión
    0.52
     scall
    0.49
    
    0.49
    ColumnHeaders
    0.48
    +')
    0.48
     हीट
    0.46
     öner
    0.46
    पाउंड
    0.46
    akas
    0.46
    Activations Density 0.000%

    No Known Activations