© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 200291
    Prev
    Next
    INDEX
    Explanations

    Typically

    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_37_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
     spring
    0.70
     Spring
    0.63
     autumn
    0.63
    autumn
    0.61
    SPRING
    0.60
    spring
    0.60
     printemps
    0.60
    Spring
    0.59
     SPRING
    0.56
    春
    0.54
    POSITIVE LOGITS
     Week
    0.62
     week
    0.56
     सप्ताह
    0.53
    週
    0.51
     semana
    0.49
    Week
    0.49
     WEEK
    0.49
     недель
    0.48
     সপ্তাহ
    0.47
     труда
    0.45
    Activations Density 0.002%

    No Known Activations