© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14613
    Prev
    Next
    INDEX
    Explanations

    coding snippets, unicode literals

    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_40_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
    qualification
    0.38
     चंद
    0.38
     qualify
    0.37
    रावट
    0.37
     `
    0.37
     شخصیت
    0.37
    navbarNav
    0.36
     qualifications
    0.35
    OOOO
    0.35
     myst
    0.34
    POSITIVE LOGITS
     u
    1.38
     unicode
    0.85
    unicode
    0.83
     Unicode
    0.79
    u
    0.78
     ع
    0.78
    Unicode
    0.75
     उ
    0.74
    𝑢
    0.72
    う
    0.70
    Activations Density 0.146%

    No Known Activations