© 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
    2. Gemma-3-27B-IT
    3. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 157273
    Prev
    Next
    INDEX
    Explanations

    temples

    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_50_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
    Clark
    0.43
     Flint
    0.43
    فت
    0.42
     जीबी
    0.40
     crít
    0.38
    ***",
    0.38
    ޝ
    0.38
     Clin
    0.37
    ריה
    0.37
     ..$
    0.36
    POSITIVE LOGITS
     хра
    1.55
     temple
    1.53
     Temple
    1.44
    Temple
    1.40
     मंदिर
    1.37
     temples
    1.33
     храм
    1.27
     templo
    1.25
     মন্দির
    1.19
     मंदिरों
    1.16
    Activations Density 0.000%

    No Known Activations