© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 222914
    Prev
    Next
    INDEX
    Explanations

    statement attribution

    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
    t
    0.70
     اڈوں
    0.67
     invités
    0.64
    チーズ
    0.64
    在
    0.64
    在意
    0.62
     حصہ
    0.61
    ைட்
    0.60
     povos
    0.60
    ন্যায়
    0.60
    POSITIVE LOGITS
    :
    0.71
    (
    0.66
    4
    0.64
    /
    0.63
    .
    0.58
     bagi
    0.57
     shank
    0.57
    линд
    0.57
    "
    0.57
    5
    0.57
    Activations Density 0.001%

    No Known Activations