© 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. 6128
    Prev
    Next
    INDEX
    Explanations

    Venn Diagram

    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
     risultato
    0.40
    अनि
    0.40
    Chia
    0.39
     Обра
    0.37
    Opacity
    0.37
    Обра
    0.36
     спи
    0.36
    Simon
    0.36
    ansson
    0.36
     값
    0.35
    POSITIVE LOGITS
     De
    1.15
    De
    1.03
     de
    0.72
     де
    0.61
     Euler
    0.59
    <0xA4>
    0.57
     DE
    0.57
    德
    0.56
    de
    0.56
     देहरादून
    0.54
    Activations Density 0.070%

    No Known Activations