© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 62323
    Prev
    Next
    INDEX
    Explanations

    apostrophe

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    เข
    0.58
     він
    0.54
    他
    0.54
     he
    0.51
     он
    0.51
     เข
    0.51
     He
    0.50
     Он
    0.46
    He
    0.46
    ’
    0.46
    POSITIVE LOGITS
     book
    0.72
     کتاب
    0.66
     книга
    0.63
     livro
    0.61
     libro
    0.59
    book
    0.59
     książ
    0.58
     किताब
    0.57
    पुस्तक
    0.57
     책
    0.56
    Activations Density 0.005%

    No Known Activations