© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 150088
    Prev
    Next
    INDEX
    Explanations

    say "s" 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_59_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
     приходит
    0.43
    (_
    0.42
    expects
    0.42
     считает
    0.39
     debe
    0.38
     necesita
    0.38
     heeft
    0.38
    –
    0.38
     يريد
    0.38
     принимает
    0.37
    POSITIVE LOGITS
     прода
    0.54
    SPEAK
    0.51
     berbicara
    0.48
     falar
    0.47
    sell
    0.47
     penjualan
    0.47
    売
    0.47
    speak
    0.47
     konuş
    0.46
    ขาย
    0.46
    Activations Density 0.009%

    No Known Activations