© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 197864
    Prev
    Next
    INDEX
    Explanations

    say "d" words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     quel
    0.38
     quelle
    0.37
     du
    0.36
    笠
    0.36
     stamp
    0.35
    了我
    0.35
    AMOS
    0.34
    하는데
    0.34
     part
    0.34
     રહ્યું
    0.34
    POSITIVE LOGITS
    说话
    0.43
     मनो
    0.41
     дово
    0.40
    &&\
    0.40
    ভাত
    0.40
     Childhood
    0.40
     ölç
    0.40
    顯
    0.39
    钦
    0.39
    潮
    0.38
    Activations Density 0.001%

    No Known Activations