© 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. 27263
    Prev
    Next
    INDEX
    Explanations

    man

    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
    ўся
    0.31
     популација
    0.29
    ２
    0.29
    نيف
    0.29
    нага
    0.29
    軻
    0.29
    BleStatus
    0.29
     zewnętrzne
    0.29
    ၂
    0.29
    ೨
    0.28
    POSITIVE LOGITS
    an
    0.44
    ik
    0.38
    ü
    0.37
    es
    0.37
    t
    0.36
    im
    0.34
    ob
    0.33
    ia
    0.32
    ti
    0.32
    '
    0.32
    Activations Density 0.020%

    No Known Activations