© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109272
    Prev
    Next
    INDEX
    Explanations

    decoration or text-decoration

    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_2_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
     it
    1.58
     be
    1.50
     as
    1.50
     for
    1.45
     at
    1.33
    س
    1.30
    1
    1.23
    あ
    1.23
     are
    1.21
    ED
    1.21
    POSITIVE LOGITS
    ни
    1.12
    ва
    1.12
    ים
    1.11
    들이
    1.02
    스를
    1.02
    នៃ
    1.00
    ть
    0.97
    ка
    0.91
     режима
    0.87
    лога
    0.87
    Activations Density 0.001%

    No Known Activations