© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132427
    Prev
    Next
    INDEX
    Explanations

    semantical

    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_6_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
    at
    1.41
    ic
    1.22
    ure
    1.15
    ha
    0.99
    с
    0.98
    ны
    0.95
    ست
    0.95
    ä
    0.93
    ia
    0.93
    IN
    0.91
    POSITIVE LOGITS
    り
    1.51
    ໃນ
    1.26
     İyi
    1.15
    ಮ
    1.14
    제의
    1.09
     Бүгенге
    1.09
    在
    1.09
     allemand
    1.09
    Một
    1.07
    kých
    1.06
    Activations Density 0.003%

    No Known Activations