© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 15207
    Prev
    Next
    INDEX
    Explanations

    gold, silver jewelry

    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_15_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
    ي
    0.64
     NÃO
    0.57
    کا
    0.55
    Ꮙ
    0.55
     Су
    0.54
     પેટ્રોલ
    0.54
    يون
    0.54
    ରା
    0.54
    不會
    0.53
     ۳
    0.52
    POSITIVE LOGITS
     idem
    0.65
     kunna
    0.55
    ht
    0.48
     πληροφο
    0.48
    something
    0.47
     Woodstock
    0.47
     kunne
    0.46
    annis
    0.46
    ters
    0.46
    there
    0.46
    Activations Density 0.003%

    No Known Activations