© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134937
    Prev
    Next
    INDEX
    Explanations

    business regulations and agencies

    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_6_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
    1
    1.02
    ak
    0.99
    0
    0.98
    cs
    0.95
    set
    0.88
    keb
    0.86
    setzen
    0.84
    كيت
    0.84
    ls
    0.83
    krank
    0.82
    POSITIVE LOGITS
    は
    1.18
    는
    1.16
    ۔
    1.07
    یا
    1.03
     fortnight
    1.00
     monochromatic
    0.97
    ના
    0.97
    نی
    0.96
    دی
    0.96
     percolation
    0.95
    Activations Density 0.000%

    No Known Activations