© 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. 27235
    Prev
    Next
    INDEX
    Explanations

    walked by

    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
    a
    0.98
    func
    0.73
    く
    0.68
    e
    0.67
    Q
    0.64
    k
    0.63
    ジュ
    0.59
    の
    0.59
    an
    0.58
    ხვევ
    0.58
    POSITIVE LOGITS
    𝐭
    0.79
     个
    0.67
     ت
    0.66
     गाडी
    0.65
     پ
    0.64
     用户
    0.64
     emotions
    0.62
     ס
    0.62
     פ
    0.62
     irreparable
    0.61
    Activations Density 0.005%

    No Known Activations