© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24103
    Prev
    Next
    INDEX
    Explanations

    followed by colon and text

    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
    Negative Logits
    一
    0.43
    uq
    0.41
    أ
    0.39
    ur
    0.38
    本
    0.38
    L
    0.35
    at
    0.35
    中
    0.34
    ig
    0.34
     Arts
    0.33
    POSITIVE LOGITS
    ла
    0.45
     deportivas
    0.44
    ки
    0.43
    la
    0.43
    li
    0.42
     are
    0.42
    い
    0.42
     tecnológicas
    0.40
     curvas
    0.40
     futuras
    0.39
    Activations Density 0.114%

    No Known Activations