© 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. 78160
    Prev
    Next
    INDEX
    Explanations

    parentheses with following descriptors

    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
    ي
    2.14
     is
    1.86
     of
    1.70
    리
    1.54
    أ
    1.48
    ك
    1.42
    다
    1.39
    ２
    1.30
    ج
    1.29
    ون
    1.27
    POSITIVE LOGITS
    :
    1.74
    的时
    1.46
    itie
    1.45
    ai
    1.27
    اً
    1.25
    ası
    1.21
    اک
    1.20
     второй
    1.20
    itin
    1.19
     carboxylic
    1.13
    Activations Density 0.019%

    No Known Activations