© 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. 145473
    Prev
    Next
    INDEX
    Explanations

    foreign word 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_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
    ل
    1.35
     for
    1.20
     as
    1.17
    ：
    1.17
    ch
    1.13
     Paragon
    1.12
     \
    1.09
     fallback
    1.09
    、
    1.09
     konfigur
    1.07
    POSITIVE LOGITS
    는
    2.59
    ا
    2.34
    ா
    1.94
    া
    1.91
    は
    1.82
    ি
    1.81
    를
    1.81
    та
    1.77
    是
    1.75
    ా
    1.75
    Activations Density 0.000%

    No Known Activations