© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 202500
    Prev
    Next
    INDEX
    Explanations

    import json

    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_37_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
    評
    0.39
    astrophe
    0.38
    ீடு
    0.38
    falling
    0.37
     falling
    0.37
     aba
    0.37
    forest
    0.37
    fallback
    0.36
    された
    0.36
    Partido
    0.35
    POSITIVE LOGITS
     উক
    0.43
    ख़
    0.39
     линей
    0.38
    خیص
    0.37
    ᱷ
    0.37
     توڑ
    0.36
     Wen
    0.36
     лечения
    0.36
     ब्लूटूथ
    0.36
     பாத
    0.36
    Activations Density 0.001%

    No Known Activations