Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 165819
    Prev
    Next
    INDEX
    Explanations

    relates

    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_13_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
     Añ
    0.51
     authors
    0.49
    à
    0.47
     accounted
    0.46
     وطالبات
    0.46
     obtained
    0.45
     بابەت
    0.45
     account
    0.44
     considera
    0.43
     বাঁধবেন
    0.43
    POSITIVE LOGITS
    ిన
    0.48
     Trains
    0.45
    ணு
    0.44
    伴
    0.44
     acompañado
    0.42
    იკ
    0.42
    Inet
    0.42
     Trainings
    0.41
     Questions
    0.40
    ッション
    0.40
    Activations Density 0.003%

    No Known Activations