© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 47343
    Prev
    Next
    INDEX
    Explanations

    a nivel seguido de sustantivo

    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_3_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
    ன்
    0.84
    :
    0.74
    ும்
    0.72
    вав
    0.72
    horns
    0.69
     رکھیں
    0.69
    ев
    0.68
    ı
    0.67
    ት
    0.65
    ီ
    0.65
    POSITIVE LOGITS
    지
    1.16
    ف
    0.98
     to
    0.90
    ر
    0.87
    to
    0.84
    m
    0.80
    ب
    0.80
    ات
    0.80
    ج
    0.77
    0
    0.76
    Activations Density 0.066%

    No Known Activations