© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 137641
    Prev
    Next
    INDEX
    Explanations

    Zelda: Tears of the Kingdom

    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_37_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
     ജില്ല
    0.45
    🌖
    0.42
    kab
    0.42
    Kab
    0.39
     मैनपुरी
    0.39
    hams
    0.38
    櫥
    0.38
    న్‌
    0.36
    िलं
    0.36
    ҹ
    0.36
    POSITIVE LOGITS
     Nintendo
    0.47
     ami
    0.44
     bre
    0.42
     Ami
    0.40
     tak
    0.39
    ampu
    0.39
     sensores
    0.38
     shear
    0.38
    Nintendo
    0.38
    ారీ
    0.37
    Activations Density 0.001%

    No Known Activations