© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48584
    Prev
    Next
    INDEX
    Explanations

    complex, magic, science, exact

    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_10_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
    季
    0.40
    ر
    0.38
    ос
    0.38
    о
    0.37
    р
    0.36
     lớp
    0.36
    ل
    0.36
    ور
    0.35
     LayoutInflater
    0.34
    ቃዎች
    0.34
    POSITIVE LOGITS
    t
    0.64
     imaginar
    0.45
     podría
    0.43
     máxima
    0.40
     współ
    0.40
     incite
    0.40
     conectar
    0.39
     Buck
    0.39
    tttt
    0.39
     todavía
    0.38
    Activations Density 0.057%

    No Known Activations