© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 51630
    Prev
    Next
    INDEX
    Explanations

    decade

    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_10_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
    การ
    0.29
     μεγάλη
    0.28
    不
    0.28
    itado
    0.23
    θηκε
    0.23
    地方
    0.22
     Congressman
    0.22
     permesso
    0.22
    ック
    0.22
    വില്‍
    0.22
    POSITIVE LOGITS
    require
    0.26
     използва
    0.26
    ץ
    0.26
    War
    0.26
    intensity
    0.25
    рят
    0.25
     categor
    0.25
     require
    0.24
    Watts
    0.24
    place
    0.24
    Activations Density 0.004%

    No Known Activations