© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 207250
    Prev
    Next
    INDEX
    Explanations

    are

    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
     completion
    0.42
    Ω
    0.37
     Completion
    0.37
     THEY
    0.36
     yen
    0.35
     IN
    0.35
     கட்டப்பட்டது
    0.34
    那麼
    0.34
    છી
    0.33
    嶄
    0.33
    POSITIVE LOGITS
    class
    0.60
     class
    0.57
     класса
    0.50
    类
    0.49
     Klasse
    0.47
     کلاس
    0.47
    类的
    0.47
     класс
    0.47
     clase
    0.46
     klasse
    0.45
    Activations Density 0.004%

    No Known Activations