© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 219345
    Prev
    Next
    INDEX
    Explanations

    Ryzen CPUs

    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_47_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
    abez
    0.39
     ❤️
    0.39
     recurring
    0.38
     ③
    0.38
     &
    0.38
     ❤
    0.38
    nh
    0.37
     ♡
    0.37
    ళ
    0.37
     Δ
    0.36
    POSITIVE LOGITS
    住所
    0.43
    没事
    0.41
     उज्ज
    0.37
     अभिव्यक्ति
    0.37
     മാലി
    0.37
     नाइन
    0.36
     érté
    0.36
    گانی
    0.36
     computations
    0.35
    ্মা
    0.35
    Activations Density 0.003%

    No Known Activations