© 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. 51787
    Prev
    Next
    INDEX
    Explanations

    good quality

    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
    ٨
    0.54
     effectués
    0.51
    在
    0.51
    ره
    0.48
    eng
    0.47
    لا
    0.45
     خودرو
    0.44
    li
    0.43
    ٤
    0.43
    يد
    0.43
    POSITIVE LOGITS
    of
    0.70
    ’
    0.58
     formulate
    0.57
    考え
    0.53
     of
    0.53
    ต์
    0.50
     nipples
    0.50
    υτό
    0.47
    ของ
    0.47
    ק
    0.47
    Activations Density 0.004%

    No Known Activations