© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84790
    Prev
    Next
    INDEX
    Explanations

    minimum requirements or conditions

    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_0_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    с
    1.66
    ス
    1.66
    ك
    1.63
    к
    1.59
    اری
    1.57
    手術
    1.38
    設定
    1.34
    リ
    1.34
    み
    1.25
    見
    1.25
    POSITIVE LOGITS
    A
    1.68
    T
    1.59
    ↵
    1.58
    i
    1.55
    0
    1.51
    W
    1.49
    M
    1.44
    H
    1.44
    w
    1.37
    d
    1.35
    Activations Density 0.000%

    No Known Activations