© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11750
    Prev
    Next
    INDEX
    Explanations

    magazines and magazine covers

    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
    ק
    0.40
    c
    0.39
    e
    0.39
    ما
    0.38
    ده
    0.38
    ê
    0.36
    st
    0.36
    ")
    0.35
    ed
    0.35
    Â
    0.35
    POSITIVE LOGITS
     Magazines
    0.54
    雑誌
    0.48
     magazines
    0.46
    杂志
    0.43
     MAGAZINE
    0.39
    urias
    0.39
     revistas
    0.38
    Vish
    0.38
     Magazine
    0.37
     magazine
    0.36
    Activations Density 0.021%

    No Known Activations