© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 88828
    Prev
    Next
    INDEX
    Explanations

    etc

    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_11_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
     on
    0.63
    N
    0.61
    ור
    0.60
    Civ
    0.59
    ور
    0.58
     Gen
    0.58
    Leg
    0.58
    al
    0.57
    ర
    0.55
    C
    0.55
    POSITIVE LOGITS
    ünüz
    0.67
     punctatis
    0.60
     gesturing
    0.59
     опыт
    0.57
     دھو
    0.57
    𝚐
    0.57
     плану
    0.57
     katılı
    0.57
     ลํา
    0.56
     lymphatiques
    0.55
    Activations Density 0.010%

    No Known Activations