© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88992
    Prev
    Next
    INDEX
    Explanations

    abbreviations PGF, IPT

    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_3_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
    يي
    0.88
    لي
    0.82
    ות
    0.78
    ي
    0.77
    。
    0.71
    ية
    0.71
    য়
    0.71
    но
    0.69
    lık
    0.69
    ิต
    0.68
    POSITIVE LOGITS
    ن
    0.64
     ל
    0.62
     vouloir
    0.60
     conceivable
    0.59
    flin
    0.59
     सुधा
    0.58
     retrou
    0.57
    ム
    0.57
     supposing
    0.56
     подачи
    0.55
    Activations Density 0.000%

    No Known Activations