© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 103252
    Prev
    Next
    INDEX
    Explanations

    technical IT articles

    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_16_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
    olojik
    0.52
    लेले
    0.49
    años
    0.49
    ្អ
    0.48
    lah
    0.47
     afstand
    0.47
    tiden
    0.46
     tief
    0.46
    মেয়
    0.46
    椑
    0.46
    POSITIVE LOGITS
     জ্যোতি
    0.42
    Servlet
    0.41
    Jimmy
    0.41
    Reporter
    0.41
     resveratrol
    0.40
    ﺴ
    0.40
     uyg
    0.40
    UY
    0.39
     samoglas
    0.39
    Settl
    0.39
    Activations Density 0.000%

    No Known Activations