© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58214
    Prev
    Next
    INDEX
    Explanations

    wrestling matches, rumble matches

    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_11_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
     croche
    0.51
    ಔ
    0.47
     Rouge
    0.46
     Alph
    0.46
    mäss
    0.46
    स्टर
    0.46
    ograd
    0.45
     Albania
    0.45
    Gym
    0.45
     Aper
    0.45
    POSITIVE LOGITS
    精力
    0.48
    。
    0.48
    流程
    0.46
    ่น
    0.46
     вскоре
    0.46
    reshape
    0.45
    かった
    0.45
    到现在
    0.45
    character
    0.44
    edge
    0.44
    Activations Density 0.004%

    No Known Activations