© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36538
    Prev
    Next
    INDEX
    Explanations

    watashi wa / I am

    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_3_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
     rédu
    0.81
     сообще
    0.78
     développ
    0.77
     atteint
    0.77
     і
    0.76
     в
    0.75
     permettra
    0.75
     myriad
    0.75
     transmettre
    0.73
     diminu
    0.72
    POSITIVE LOGITS
    u
    1.03
    in
    1.02
    i
    0.96
    d
    0.96
    ي
    0.96
    V
    0.95
    و
    0.93
    W
    0.91
    A
    0.89
    ت
    0.88
    Activations Density 0.006%

    No Known Activations