© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202743
    Prev
    Next
    INDEX
    Explanations

    Japan, not China

    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
    도
    0.29
    o
    0.27
    ک
    0.27
     ín
    0.26
    ض
    0.26
     보험
    0.25
    റില്‍
    0.25
    在
    0.24
    d
    0.24
    ର
    0.24
    POSITIVE LOGITS
     showered
    0.25
     Lok
    0.25
     Chemin
    0.24
     requested
    0.24
     Meyer
    0.24
    enie
    0.24
    eneuve
    0.24
     Ney
    0.23
    eleaf
    0.23
     Nesse
    0.23
    Activations Density 0.000%

    No Known Activations