© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38047
    Prev
    Next
    INDEX
    Explanations

    possessive particle de

    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
    пис
    0.71
    ම්
    0.68
    нэт
    0.63
    前辈
    0.61
    ්
    0.61
    пит
    0.61
    Ꮻ
    0.60
    йд
    0.59
    허
    0.59
    ጪ
    0.59
    POSITIVE LOGITS
    j
    0.63
    ri
    0.63
     interrump
    0.63
     walnuts
    0.62
     c
    0.61
    "
    0.57
     theorem
    0.57
     correspondence
    0.57
     spasm
    0.57
     caravan
    0.56
    Activations Density 0.011%

    No Known Activations