© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82973
    Prev
    Next
    INDEX
    Explanations

    u followed by other characters

    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_0_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
    리
    1.38
    де
    1.18
    ع
    1.13
    не
    1.06
    ا
    1.06
    ى
    1.05
    та
    1.04
    ж
    1.04
    اف
    1.02
    ک
    1.02
    POSITIVE LOGITS
    ological
    0.93
    -
    0.90
    ado
    0.88
    กับ
    0.88
    not
    0.83
    ator
    0.82
    masına
    0.81
     pří
    0.78
    anie
    0.78
    ův
    0.77
    Activations Density 0.000%

    No Known Activations