© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33682
    Prev
    Next
    INDEX
    Explanations

    `torch` code snippets

    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_40_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
     канали
    0.40
    익
    0.40
     FITNESS
    0.39
    פתח
    0.39
     канал
    0.39
    Ux
    0.39
    䄱
    0.38
     জ্বাল
    0.38
     π
    0.37
    oux
    0.37
    POSITIVE LOGITS
     spectra
    0.40
    scopes
    0.40
     Models
    0.37
    ビング
    0.37
     Kyr
    0.37
    Models
    0.36
     modèles
    0.36
    lare
    0.36
    models
    0.35
     modelos
    0.35
    Activations Density 0.005%

    No Known Activations