© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44295
    Prev
    Next
    INDEX
    Explanations

    tea accessories (茶匙, 茶漏)

    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_3_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
    는
    1.02
    ро
    0.88
    р
    0.78
    pm
    0.73
    symplectic
    0.73
    ى
    0.73
    pecific
    0.70
    rossovers
    0.70
    efficients
    0.69
    personas
    0.69
    POSITIVE LOGITS
    0.89
     acestea
    0.68
     HDD
    0.68
    ="
    0.67
     piscine
    0.67
     UX
    0.67
     jaren
    0.66
     جهاز
    0.65
    Z
    0.64
    N
    0.63
    Activations Density 0.003%

    No Known Activations