© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 140832
    Prev
    Next
    INDEX
    Explanations

    Asia-Pacific regions

    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_46_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
     Far
    2.88
    Far
    2.75
    far
    1.98
     far
    1.98
     FAR
    1.89
    FAR
    1.89
    远
    1.81
    遠
    1.68
     فار
    1.66
     фар
    1.66
    POSITIVE LOGITS
    τό
    0.37
    ↔
    0.35
    тися
    0.34
    flin
    0.34
     airs
    0.33
    غراف
    0.33
    ذية
    0.33
    付
    0.33
    ☛
    0.33
    驀
    0.33
    Activations Density 0.008%

    No Known Activations