© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107097
    Prev
    Next
    INDEX
    Explanations

    French words<ctrl63>

    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_2_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
    νό
    1.30
    н
    1.28
    ν
    1.23
    ید
    1.02
    ğine
    1.00
    avu
    0.99
     sanitized
    0.98
     지금까지
    0.97
     ልዩ
    0.94
     coveted
    0.90
    POSITIVE LOGITS
    ك
    1.67
    ot
    1.42
    ح
    1.34
    et
    1.33
    ون
    1.31
    ur
    1.28
    at
    1.27
    ת
    1.21
    e
    1.20
    ।
    1.20
    Activations Density 0.001%

    No Known Activations