© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4356
    Prev
    Next
    INDEX
    Explanations

    Ghana

    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_39_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
     federally
    0.37
     Immunity
    0.37
     alde
    0.36
     LZ
    0.36
     coral
    0.36
    federal
    0.34
     Ols
    0.34
    딜
    0.34
     Rp
    0.33
     recept
    0.33
    POSITIVE LOGITS
     Ghana
    1.38
    Ghana
    1.38
     Ghanaian
    1.34
     Ghanaians
    1.31
     Accra
    1.22
     Akufo
    0.99
    Nana
    0.95
     Nana
    0.94
     Ashanti
    0.91
     Mahama
    0.86
    Activations Density 0.007%

    No Known Activations