© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18956
    Prev
    Next
    INDEX
    Explanations

    selection, carry, specialize

    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_34_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
     নিলাম
    0.47
     सूख
    0.40
    }}^{*}
    0.38
     auctions
    0.38
     zákaz
    0.37
     offered
    0.37
    の説明
    0.37
     नीला
    0.37
     skle
    0.36
    apple
    0.36
    POSITIVE LOGITS
     присутствует
    0.45
     hadir
    0.39
    IDE
    0.38
     присут
    0.38
     Agreed
    0.37
    zec
    0.37
    ﮢ
    0.37
     উপস্থিতি
    0.37
     석
    0.35
    Дан
    0.35
    Activations Density 0.016%

    No Known Activations