© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 5921
    Prev
    Next
    INDEX
    Explanations

    Italian language and Italy content

    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_38_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
     Испа
    0.50
     испан
    0.48
     दि
    0.48
     Испании
    0.47
    вание
    0.46
     mojo
    0.46
     bukan
    0.46
    𝚢
    0.46
     салу
    0.45
     ఆ
    0.45
    POSITIVE LOGITS
     partecip
    1.02
     Italian
    0.99
    Università
    0.99
     caratter
    0.97
     più
    0.96
     città
    0.96
    Italian
    0.96
    イタリア
    0.96
     Grazie
    0.95
     Scuola
    0.95
    Activations Density 0.093%

    No Known Activations