© 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. 30173
    Prev
    Next
    INDEX
    Explanations

    daily weather forecast

    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
    PreferredItem
    0.36
     ബ്രി
    0.34
     заги
    0.34
    igneur
    0.34
     ड्यू
    0.34
    ड्यू
    0.33
    примеча
    0.33
    \}^{
    0.33
     увидел
    0.33
     brind
    0.33
    POSITIVE LOGITS
     malfunctioning
    0.34
    regarding
    0.33
     Thursday
    0.33
     Wednesday
    0.32
    বদ
    0.31
     OB
    0.31
     regarding
    0.31
    Hun
    0.31
    MP
    0.31
    ম
    0.31
    Activations Density 0.002%

    No Known Activations