© 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. 87600
    Prev
    Next
    INDEX
    Explanations

    French words or parts of words

    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
    ↵
    0.80
     by
    0.69
    '
    0.62
    ก
    0.56
     Petition
    0.55
    Ö
    0.54
    kých
    0.54
    O
    0.51
    ura
    0.50
    ät
    0.50
    POSITIVE LOGITS
    tareas
    0.75
    া
    0.70
    𝙙
    0.70
    ா
    0.67
    지만
    0.66
     प्रमाणात
    0.66
    IamPermissions
    0.66
    др
    0.64
    𝗱
    0.63
     ކުރ
    0.63
    Activations Density 0.001%

    No Known Activations