© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 174694
    Prev
    Next
    INDEX
    Explanations

    go-to choice/method/language

    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_24_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
     kisi
    0.42
    ទំនង
    0.41
    play
    0.40
     intimately
    0.38
    instell
    0.37
     독립
    0.36
    Kon
    0.36
     земли
    0.36
     जमीन
    0.36
     &-
    0.36
    POSITIVE LOGITS
     gerar
    0.43
     erad
    0.43
     brigade
    0.42
    ডিট
    0.41
     prevent
    0.40
     ພວກເຮົາ
    0.40
     আমরা
    0.39
     autocl
    0.39
     remove
    0.39
     我们
    0.39
    Activations Density 0.005%

    No Known Activations