© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164787
    Prev
    Next
    INDEX
    Explanations

    Hagia Sophia and mosques

    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_13_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
     कार्ट
    0.56
    ONT
    0.51
    𝐎
    0.50
     मार्
    0.50
     Institutes
    0.49
    水
    0.49
     프로세
    0.49
    <unused53>
    0.48
     ଦ
    0.48
    ͚
    0.48
    POSITIVE LOGITS
    ان
    0.54
    ром
    0.49
     nacional
    0.46
     Agus
    0.46
    national
    0.46
    рез
    0.46
     national
    0.45
    χεία
    0.45
     espec
    0.45
     ıs
    0.44
    Activations Density 0.001%

    No Known Activations