© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38155
    Prev
    Next
    INDEX
    Explanations

    gaining momentum

    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_11_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
    m
    0.86
    s
    0.77
     Textiles
    0.72
     Economics
    0.71
     Derivatives
    0.69
    𝗮
    0.69
    y
    0.68
     Overview
    0.67
    𝐨
    0.67
     Alumni
    0.66
    POSITIVE LOGITS
    rotate
    0.64
    ূতন
    0.58
    Vida
    0.56
    Rotate
    0.55
     clump
    0.55
    Proyecto
    0.55
    Teste
    0.54
    Siempre
    0.54
    set
    0.54
     صعبه
    0.54
    Activations Density 0.001%

    No Known Activations