© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29704
    Prev
    Next
    INDEX
    Explanations

    Mexico

    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_40_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
    лад
    0.44
    nard
    0.40
    다운
    0.39
     கூ
    0.39
     TimeSpan
    0.37
     खान
    0.37
     Request
    0.37
    <0x84>
    0.36
     download
    0.36
    डब्ल्यू
    0.35
    POSITIVE LOGITS
     mex
    0.41
    죵
    0.39
     Mexiko
    0.38
     Meks
    0.37
     Gén
    0.37
     тканей
    0.37
    MEX
    0.36
    érien
    0.36
     México
    0.35
    ría
    0.35
    Activations Density 0.078%

    No Known Activations