© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133824
    Prev
    Next
    INDEX
    Explanations

    Arabic prefixes and suffixes

    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_1_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
    ل
    1.09
    τε
    0.98
    ни
    0.95
    リ
    0.95
     खिताब
    0.91
    тах
    0.89
    лиза
    0.89
    人
    0.88
    عت
    0.85
    к
    0.85
    POSITIVE LOGITS
    j
    1.11
    it
    1.05
     are
    1.02
    ın
    1.00
    '
    0.91
    7
    0.89
    .
    0.87
    8
    0.83
    a
    0.82
    ut
    0.79
    Activations Density 0.003%

    No Known Activations