© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 64326
    Prev
    Next
    INDEX
    Explanations

    Norway

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Schul
    0.43
     gericht
    0.40
     Marshall
    0.38
     |
    0.37
     Dan
    0.36
    frank
    0.36
     Watson
    0.36
    artikel
    0.35
     Lehr
    0.35
     Detroit
    0.34
    POSITIVE LOGITS
     Norway
    0.93
     Norweg
    0.87
     النرويج
    0.87
    Norway
    0.85
     Norwegian
    0.84
     norsk
    0.82
     Norwegen
    0.78
     Trond
    0.75
    挪
    0.69
     Oslo
    0.68
    Activations Density 0.001%

    No Known Activations