© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86119
    Prev
    Next
    INDEX
    Explanations

    Tifinagh, Arabic, Hebrew, Greek, Berber 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_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
    t
    1.27
    an
    1.20
    ت
    0.98
    a
    0.97
    ان
    0.86
    lene
    0.82
    l
    0.82
    tiff
    0.82
    lis
    0.81
    lung
    0.81
    POSITIVE LOGITS
    로
    1.21
     և
    1.01
     și
    0.96
    도
    0.85
     وأ
    0.84
     מ
    0.84
     deix
    0.82
     וה
    0.79
     וא
    0.77
    ו
    0.77
    Activations Density 0.000%

    No Known Activations