© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81494
    Prev
    Next
    INDEX
    Explanations

    du, duper, duolingo, duper, duper, duper, duper, duper, duper

    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_0_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
    o
    2.19
    a
    1.97
    -
    1.71
    e
    1.63
     a
    1.57
    ag
    1.52
    ↵
    1.45
    em
    1.45
    im
    1.40
    ও
    1.39
    POSITIVE LOGITS
    ८
    1.09
     demikian
    1.07
     こんにちは
    1.02
    ၿ
    1.01
     changement
    0.98
     проблему
    0.98
     promulgating
    0.98
     constater
    0.96
    о
    0.95
     for
    0.95
    Activations Density 0.001%

    No Known Activations