© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102879
    Prev
    Next
    INDEX
    Explanations

    appropriate content and relationships

    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_14_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
     Medizin
    0.20
    fallback
    0.19
     stratégie
    0.18
    alcoholic
    0.18
     場
    0.18
    ందు
    0.18
     可愛い
    0.17
    पतवार
    0.17
     pistola
    0.17
    ⣀
    0.17
    POSITIVE LOGITS
    ॉल
    0.18
     om
    0.17
     GRE
    0.17
     Sm
    0.17
     correlations
    0.16
     Spotlight
    0.16
     bridges
    0.16
     internet
    0.16
     Oak
    0.16
     connects
    0.16
    Activations Density 0.002%

    No Known Activations