© 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. 45110
    Prev
    Next
    INDEX
    Explanations

    onCreate(Bundle savedInstanceState)

    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
    는
    0.68
    的
    0.63
    ة
    0.58
     историю
    0.57
    与其他
    0.57
    の
    0.57
    에
    0.57
    ির
    0.56
    ابہ
    0.56
    的核心
    0.54
    POSITIVE LOGITS
    m
    0.73
     gär
    0.70
    すぎ
    0.64
    always
    0.63
     juu
    0.63
     be
    0.63
     them
    0.62
     itd
    0.59
    Usually
    0.59
     purify
    0.59
    Activations Density 0.000%

    No Known Activations