© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202763
    Prev
    Next
    INDEX
    Explanations

    words ending in "v" followed by "ailing"

    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_6_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
    as
    0.84
    ar
    0.79
    an
    0.76
    n
    0.70
    u
    0.69
    ad
    0.69
    mer
    0.66
    2
    0.59
    ed
    0.59
    rate
    0.56
    POSITIVE LOGITS
    ון
    0.68
    بي
    0.62
     άνθρω
    0.57
    乆
    0.56
     secu
    0.55
     officielles
    0.55
     It
    0.54
     conqu
    0.52
     presentes
    0.52
     fabricantes
    0.52
    Activations Density 0.000%

    No Known Activations