© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 57727
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    ła
    1.18
    ார்
    1.08
     and
    1.07
    t
    1.05
    acije
    1.04
    혔
    1.02
     or
    0.98
    وری
    0.98
    щий
    0.98
    tch
    0.97
    POSITIVE LOGITS
    1.35
    ul
    1.28
    ла
    1.28
    n
    1.19
    ล
    1.14
    н
    1.09
    ना
    1.05
    č
    1.03
    ER
    1.02
    ü
    1.01
    Activations Density 0.000%

    No Known Activations