© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 26782
    Prev
    Next
    INDEX
    Explanations

    numbers and periods in lists

    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_40_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
     throne
    0.52
     thrones
    0.49
     Throne
    0.46
     सिंहासन
    0.44
     trono
    0.44
     thru
    0.38
     வரி
    0.37
    thru
    0.37
    긔
    0.35
     Clas
    0.35
    POSITIVE LOGITS
     клу
    0.37
    sled
    0.37
     quid
    0.36
    溶
    0.36
     neque
    0.35
     aqueous
    0.35
     arena
    0.34
     Aqueous
    0.34
    目が
    0.34
     lãi
    0.34
    Activations Density 0.042%

    No Known Activations