© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165079
    Prev
    Next
    INDEX
    Explanations

    Mongolia and associated names

    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_13_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
     Haji
    0.49
     Thakur
    0.49
    ങ്ങ
    0.47
     Hanoi
    0.47
    Ihr
    0.46
    Beijing
    0.46
    ക്ക
    0.46
    弔
    0.46
     odlič
    0.45
     Beijing
    0.44
    POSITIVE LOGITS
    ers
    0.77
    er
    0.56
    页
    0.55
    elines
    0.55
    mento
    0.55
     Andal
    0.54
    menes
    0.53
     تے
    0.53
     기반
    0.52
    ERS
    0.52
    Activations Density 0.001%

    No Known Activations