© 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. 35063
    Prev
    Next
    INDEX
    Explanations

    проходить, пройти, проходить сквозь

    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
     ایکسپ
    0.70
     Foire
    0.65
    ルダー
    0.63
     Existem
    0.62
     zahlreichen
    0.61
     aproximadamente
    0.60
     Información
    0.59
     Ejército
    0.59
    +'.
    0.59
     aprox
    0.58
    POSITIVE LOGITS
     '
    0.52
    款
    0.50
     rotations
    0.47
    asyon
    0.47
    olytic
    0.47
    Volumes
    0.46
    裤
    0.46
    நர்
    0.45
     donations
    0.45
    ુર
    0.44
    Activations Density 0.004%

    No Known Activations