© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 36026
    Prev
    Next
    INDEX
    Explanations

    French and Spanish 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_7_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    i
    0.25
     The
    0.21
    1
    0.20
    at
    0.20
    ai
    0.20
    im
    0.19
    0
    0.19
    ie
    0.19
    z
    0.19
    il
    0.18
    POSITIVE LOGITS
     simonsen
    0.15
     beerCount
    0.15
     ayudan
    0.15
     شہریوں
    0.14
     atletas
    0.14
     niños
    0.14
     jugadores
    0.14
     filtros
    0.14
     ад
    0.14
     alimentos
    0.14
    Activations Density 0.004%

    No Known Activations