© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36879
    Prev
    Next
    INDEX
    Explanations

    Singlish exclamations and interjections

    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_11_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
    dering
    0.59
    ০০০
    0.53
    woorden
    0.53
     해도
    0.52
    stedet
    0.52
    m
    0.52
    造型
    0.51
    n
    0.51
    typen
    0.50
    UnaryOperation
    0.50
    POSITIVE LOGITS
     abril
    0.70
    йти
    0.62
     khoản
    0.62
     aqui
    0.61
     sutures
    0.61
     linhas
    0.61
     estrict
    0.59
     óptica
    0.59
     khuẩn
    0.59
     agonists
    0.58
    Activations Density 0.000%

    No Known Activations