© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44369
    Prev
    Next
    INDEX
    Explanations

    marriage in French/Spanish/Italian

    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_3_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
    nél
    0.90
    né
    0.81
    5
    0.80
    中
    0.75
    0
    0.74
    The
    0.73
    nál
    0.73
    nut
    0.71
    ské
    0.71
    ie
    0.70
    POSITIVE LOGITS
    </h2>
    0.84
    \
    0.81
    л
    0.79
     marrying
    0.75
    ’
    0.72
    </h3>
    0.70
    </h4>
    0.70
    </th>
    0.67
     Cosmetic
    0.66
    娶
    0.66
    Activations Density 0.003%

    No Known Activations