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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11149
    Prev
    Next
    INDEX
    Explanations

    phase, amplitude, and wave properties

    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
    Not in Any Lists

    No Comments

    Negative Logits
     McClure
    0.40
     appliquer
    0.39
    ᆢ
    0.38
     apical
    0.38
     FCI
    0.38
     Dain
    0.38
     Prov
    0.37
     Flip
    0.37
     ٹھ
    0.37
     DIO
    0.37
    POSITIVE LOGITS
    天氣
    0.41
    ベクトル
    0.41
    vector
    0.40
    Vector
    0.40
     vector
    0.39
    鰍
    0.39
     экран
    0.39
    WEATHER
    0.39
    Weather
    0.39
     벡터
    0.38
    Activations Density 0.016%

    No Known Activations