© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 137207
    Prev
    Next
    INDEX
    Explanations

    models and capabilities

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     over
    3.33
    over
    2.28
    Over
    2.28
     över
    2.17
     Over
    2.14
     über
    2.08
    過
    1.98
    过
    1.95
     над
    1.88
     OVER
    1.86
    POSITIVE LOGITS
     জ্যোতি
    0.40
     బహి
    0.40
    loglevel
    0.39
    chengladbach
    0.35
     ανο
    0.34
     terbuka
    0.33
    ToList
    0.33
    效率
    0.32
     নিম্নলিখিত
    0.32
     UpdateWindow
    0.32
    Activations Density 0.004%

    No Known Activations