© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22302
    Prev
    Next
    INDEX
    Explanations

    wide

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     اخت
    0.39
    '}}>
    0.36
    gota
    0.36
    Presenter
    0.35
    undered
    0.34
    瘋
    0.34
     actualizar
    0.34
    꿋
    0.34
    ರಿಕ
    0.33
    वट
    0.33
    POSITIVE LOGITS
     wide
    0.80
    wide
    0.68
     Wide
    0.62
    Wide
    0.61
     širo
    0.59
     touched
    0.54
     широкий
    0.52
     touch
    0.49
    ワイド
    0.49
     wider
    0.48
    Activations Density 0.184%

    No Known Activations