© 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. 88779
    Prev
    Next
    INDEX
    Explanations

    we followed by verbs

    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
     총
    0.61
     संथाल
    0.57
    uacao
    0.54
    μό
    0.52
    ારો
    0.52
     primeiras
    0.52
     केलेल्या
    0.51
    𝑀
    0.51
    ಾಂಶ
    0.51
    సాయ
    0.50
    POSITIVE LOGITS
    :
    0.61
     down
    0.61
     di
    0.58
     sogno
    0.57
    il
    0.57
    as
    0.56
    os
    0.56
     decide
    0.56
     argue
    0.56
     zijn
    0.56
    Activations Density 0.005%

    No Known Activations