© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216501
    Prev
    Next
    INDEX
    Explanations

    return quick_sort

    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_31_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
     gesetz
    0.39
     (=
    0.38
    ضافة
    0.38
    كامل
    0.36
     consisting
    0.36
     آد
    0.35
    żliw
    0.35
     completa
    0.34
     complete
    0.33
    수는
    0.33
    POSITIVE LOGITS
     катего
    0.42
    🗨
    0.40
     специальных
    0.39
     prak
    0.38
    特殊的
    0.38
     μπ
    0.37
    aphr
    0.36
     दुःख
    0.36
     kategorii
    0.36
     prominence
    0.36
    Activations Density 0.003%

    No Known Activations