© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 205756
    Prev
    Next
    INDEX
    Explanations

    Material-UI (MUI) components

    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_20_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
    azer
    0.45
    ढे
    0.42
     injunction
    0.42
    ค
    0.41
    filed
    0.41
     Janet
    0.40
    ayant
    0.39
    annt
    0.38
    德国
    0.38
    <table>
    0.37
    POSITIVE LOGITS
     situational
    0.56
    ச்சின்ன
    0.50
     episodic
    0.48
    🗡
    0.48
     Ά
    0.48
    ﺡ
    0.48
     ángulo
    0.46
     takže
    0.46
    LaunchAction
    0.46
     সাপ্তাহ
    0.45
    Activations Density 0.000%

    No Known Activations