© 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. 27511
    Prev
    Next
    INDEX
    Explanations

    python shebang lines

    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
    UN
    0.69
    Е
    0.64
    Э
    0.64
    F
    0.64
    U
    0.64
    リ
    0.63
    Α
    0.62
    А
    0.61
    É
    0.61
    ASS
    0.60
    POSITIVE LOGITS
    y
    0.82
    i
    0.77
    n
    0.71
    t
    0.69
    u
    0.68
    вими
    0.59
    '
    0.57
     политика
    0.53
    <0x80>
    0.51
    tions
    0.49
    Activations Density 0.038%

    No Known Activations