© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201335
    Prev
    Next
    INDEX
    Explanations

    Japanese invasion of Manchuria

    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
    ра
    0.55
     series
    0.48
    াব্য
    0.48
    _{
    0.47
     nearly
    0.47
    roo
    0.47
    oger
    0.46
    rm
    0.46
    リ
    0.45
    urd
    0.45
    POSITIVE LOGITS
     संघीय
    0.57
     puriso
    0.56
    devkit
    0.55
     stöd
    0.55
     సహాయ
    0.53
     blanchâtre
    0.53
     skór
    0.53
     Feder
    0.53
    लिन
    0.53
    סטי
    0.53
    Activations Density 0.003%

    No Known Activations