© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163802
    Prev
    Next
    INDEX
    Explanations

    shrimp dishes

    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_31_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
    萎
    0.38
     performans
    0.37
     canc
    0.36
     PERFORMANCE
    0.36
     εμφ
    0.36
     فت
    0.35
     মোক
    0.35
    躲
    0.35
     accion
    0.34
     канцеля
    0.34
    POSITIVE LOGITS
     Sevilla
    0.41
     बिल्
    0.40
    كيل
    0.39
    鱉
    0.38
     Medicaid
    0.38
     CIT
    0.35
     တို့
    0.35
    NavItem
    0.35
    အစိတ်အပိုင်း
    0.35
    uator
    0.34
    Activations Density 0.005%

    No Known Activations