© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157012
    Prev
    Next
    INDEX
    Explanations

    Korean and Japanese demonstratives

    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_2_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
    c
    1.28
    1.01
    ने
    0.99
    на
    0.97
    y
    0.96
    ла
    0.94
    ли
    0.93
    습니다
    0.91
    ia
    0.86
     mágico
    0.85
    POSITIVE LOGITS
     by
    1.27
     for
    1.13
     huit
    0.92
    ים
    0.89
     вось
    0.84
    ی
    0.83
    ä
    0.83
    یی
    0.82
    ಷ್ಣ
    0.82
    ের
    0.80
    Activations Density 0.000%

    No Known Activations