© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202471
    Prev
    Next
    INDEX
    Explanations

    japanese phrases and greetings

    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_12_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
     utile
    0.58
     hoge
    0.53
    僕
    0.50
     સેવા
    0.47
     utili
    0.47
    csv
    0.47
     chil
    0.47
    ساعد
    0.45
     útil
    0.45
     explore
    0.45
    POSITIVE LOGITS
    It
    0.57
    IamPolicy
    0.55
    Is
    0.54
     جمله
    0.52
    EditDialogOpen
    0.52
     attorney
    0.52
    म
    0.51
    ണി
    0.51
    ீஸ்
    0.51
    ം
    0.51
    Activations Density 0.003%

    No Known Activations