© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 99876
    Prev
    Next
    INDEX
    Explanations

    colors and flow

    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
    Not in Any Lists

    No Comments

    Negative Logits
    儩
    0.49
    둰
    0.48
    міну
    0.47
    Ꮬ
    0.47
    бль
    0.45
     scans
    0.45
     hashes
    0.44
     Mitgl
    0.44
    
    0.44
    Мо
    0.44
    POSITIVE LOGITS
    anya
    0.57
     Hispanics
    0.54
    :
    0.53
     robe
    0.48
     THE
    0.47
    Life
    0.47
    zeros
    0.46
     COR
    0.46
    brought
    0.46
     Life
    0.46
    Activations Density 0.000%

    No Known Activations