© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 92014
    Prev
    Next
    INDEX
    Explanations

    say "ๆ"

    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_60_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
     들
    1.42
     க
    0.72
     সমু
    0.72
    ه‌
    0.71
     môn
    0.67
     ల
    0.64
     లు
    0.64
     গুল
    0.64
     গুলি
    0.63
     கள
    0.59
    POSITIVE LOGITS
    们
    1.22
    們
    1.12
    们的
    0.96
    들은
    0.55
    たち
    0.55
    たちは
    0.55
    たちの
    0.52
    들을
    0.51
    들의
    0.49
    들에
    0.47
    Activations Density 0.001%

    No Known Activations