© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 67288
    Prev
    Next
    INDEX
    Explanations

    globalization

    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_41_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
    ရန်
    0.40
    ยาน
    0.38
    崤
    0.37
    បំ
    0.37
     spoon
    0.36
     barren
    0.36
     discharg
    0.35
    ාවිත
    0.35
    စ
    0.35
     departure
    0.34
    POSITIVE LOGITS
     globalization
    2.52
     Globalization
    2.45
     globalisation
    2.33
    Globalization
    2.31
     glaze
    1.48
    Glo
    1.34
     glazed
    1.32
     Global
    1.31
     glo
    1.30
    Global
    1.27
    Activations Density 0.004%

    No Known Activations