© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50227
    Prev
    Next
    INDEX
    Explanations

    zoning regulations and ordinances

    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_10_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
    a
    0.50
    其他
    0.43
    I
    0.40
    the
    0.40
    IRED
    0.39
    ီ
    0.38
    O
    0.38
    ↵
    0.37
    ποιή
    0.36
    how
    0.36
    POSITIVE LOGITS
    0.43
    '
    0.40
    utives
    0.38
    -
    0.38
    >
    0.36
    umā
    0.35
    "
    0.34
     -
    0.34
    -"
    0.34
    ot
    0.33
    Activations Density 0.006%

    No Known Activations