© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 133940
    Prev
    Next
    INDEX
    Explanations

    Toki Pona and other languages

    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_6_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
    \
    0.98
    4
    0.92
    <h2>
    0.91
    et
    0.89
    ats
    0.87
    _
    0.86
    9
    0.83
    ra
    0.81
    a
    0.78
    :
    0.78
    POSITIVE LOGITS
    ก
    1.08
    can
    0.98
    。
    0.97
     apoy
    0.94
    िया
    0.93
    ку
    0.92
    وم
    0.79
    0.77
    ۔
    0.77
    ።
    0.77
    Activations Density 0.004%

    No Known Activations