© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 59158
    Prev
    Next
    INDEX
    Explanations

    Klassische

    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
     הע
    0.62
    ק
    0.61
     Ahmed
    0.59
    ان
    0.55
     הס
    0.55
    v
    0.55
    ต์
    0.54
    জ
    0.54
    ഭ
    0.54
     argues
    0.53
    POSITIVE LOGITS
     क्षमताओं
    0.65
     querying
    0.62
     scanning
    0.61
     trusting
    0.60
     fooling
    0.60
     weeding
    0.59
    aton
    0.57
     sunroof
    0.55
     scaff
    0.55
     fumble
    0.55
    Activations Density 0.005%

    No Known Activations