© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136960
    Prev
    Next
    INDEX
    Explanations

    character followed by words describing roles

    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_12_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
    地方
    0.56
    是个
    0.55
    б
    0.55
     contigo
    0.50
    ση
    0.49
     उत्तरी
    0.49
    调
    0.48
    ль
    0.48
    бра
    0.48
    也是
    0.48
    POSITIVE LOGITS
    en
    0.57
     poodle
    0.56
    eman
    0.55
     مشا
    0.55
     characters
    0.55
     मिलने
    0.55
     smelling
    0.54
    ramique
    0.54
     team
    0.54
     Lampard
    0.54
    Activations Density 0.001%

    No Known Activations