© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 257026
    Prev
    Next
    INDEX
    Explanations

    holy sites and religious places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_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
     Rashford
    0.37
    HOBBIT
    0.36
    <unused624>
    0.35
     elastin
    0.34
    costcenter
    0.34
    ₂+
    0.34
     बिकॉज
    0.34
     niacin
    0.33
     threefold
    0.33
     Sasuke
    0.32
    POSITIVE LOGITS
     Temple
    0.34
    錢
    0.32
    钱
    0.31
     auxiliary
    0.31
     Opera
    0.29
     antique
    0.29
     pertaining
    0.29
     Hotel
    0.29
     money
    0.28
     D
    0.28
    Activations Density 0.001%

    No Known Activations