© 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
    2. Gemma-3-27B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 43589
    Prev
    Next
    INDEX
    Explanations

    association and association international

    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_3_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
    ца
    0.69
    НА
    0.65
    ки
    0.63
    ної
    0.63
     добав
    0.63
     Анали
    0.62
    ී
    0.61
    лав
    0.61
    ж
    0.60
    Ꮬ
    0.59
    POSITIVE LOGITS
    (
    0.89
    م
    0.70
    Base
    0.67
    Associated
    0.66
    ur
    0.62
    .
    0.62
     association
    0.61
    ende
    0.61
    ang
    0.59
    Associations
    0.58
    Activations Density 0.015%

    No Known Activations