© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167980
    Prev
    Next
    INDEX
    Explanations

    code structure delimiters

    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_31_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
    Yun
    0.40
    $).
    0.38
    ሸ
    0.36
    kovi
    0.36
    >)
    0.36
    »),
    0.36
    “)
    0.36
    kom
    0.35
    KOM
    0.35
     يون
    0.35
    POSITIVE LOGITS
     fade
    0.45
     todas
    0.44
     whenever
    0.42
     fleshy
    0.41
     ampla
    0.41
     فیصلے
    0.40
    踟
    0.40
     phases
    0.40
    ehle
    0.40
    লগ্ন
    0.40
    Activations Density 0.001%

    No Known Activations