© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131690
    Prev
    Next
    INDEX
    Explanations

    Korean place names and common words

    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_1_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
    s
    1.44
    5
    0.95
    nels
    0.94
     is
    0.94
     in
    0.90
    x
    0.88
    在
    0.88
    ch
    0.86
    يا
    0.84
    zx
    0.84
    POSITIVE LOGITS
     ولی
    0.93
    มัน
    0.90
    です
    0.88
     یا
    0.83
    の効果
    0.82
     później
    0.82
    くて
    0.81
     bukanlah
    0.80
    かけ
    0.79
    のでは
    0.79
    Activations Density 0.002%

    No Known Activations