© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 67287
    Prev
    Next
    INDEX
    Explanations

    notification

    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_51_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
     الن
    1.05
     N
    0.98
    N
    0.77
    الن
    0.65
     הנ
    0.62
     Н
    0.60
     getN
    0.56
    𝑁
    0.55
     للن
    0.54
     น
    0.53
    POSITIVE LOGITS
    notification
    0.82
     notification
    0.81
     ért
    0.77
     notified
    0.72
     Notification
    0.72
    Notification
    0.71
    notifications
    0.71
     уведом
    0.71
    通知
    0.68
    Notifications
    0.68
    Activations Density 0.002%

    No Known Activations