© 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. 34988
    Prev
    Next
    INDEX
    Explanations

    biology, medicine, and technical systems

    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
    ᅨ
    0.61
     áll
    0.56
    鐪
    0.55
    í
    0.55
     이미
    0.53
    ngx
    0.51
    이미
    0.51
    ų
    0.51
    DU
    0.49
    Í
    0.49
    POSITIVE LOGITS
    4
    0.66
    5
    0.63
    :
    0.61
     стиля
    0.58
     чувства
    0.57
    ou
    0.55
     joten
    0.54
     sculpted
    0.53
     જન્મદિવસ
    0.53
    6
    0.53
    Activations Density 0.047%

    No Known Activations