© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111557
    Prev
    Next
    INDEX
    Explanations

    French loanwords and grammatical structures

    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
    -
    1.27
     financiera
    1.07
    ’
    1.06
    s
    1.03
    д
    1.02
     materiale
    1.01
    н
    1.00
    س
    0.99
     memberi
    0.98
    น
    0.98
    POSITIVE LOGITS
    ر
    1.21
    𝗜
    1.11
     و
    0.99
     infestations
    0.99
     be
    0.97
     အ
    0.97
    I
    0.96
     а
    0.95
    ب
    0.95
     an
    0.95
    Activations Density 0.006%

    No Known Activations