© 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. 41375
    Prev
    Next
    INDEX
    Explanations

    creating and shaping objects

    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
     vuccanti
    0.63
     என்பதற்கு
    0.63
    ることが
    0.62
    습니다
    0.61
    ные
    0.61
    irman
    0.60
    ')]
    0.59
    䢍
    0.59
     нескольких
    0.56
    ')(
    0.56
    POSITIVE LOGITS
    k
    0.62
     Kin
    0.59
     na
    0.58
     s
    0.57
     auto
    0.57
     android
    0.57
     mother
    0.57
    c
    0.56
     dens
    0.55
     Gar
    0.54
    Activations Density 0.000%

    No Known Activations