© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 212743
    Prev
    Next
    INDEX
    Explanations

    PPE and safety procedures

    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_19_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
    Romania
    0.13
     Romania
    0.13
    Penalty
    0.12
    派
    0.12
    劣化
    0.12
    odef
    0.11
     spoils
    0.11
     exposes
    0.11
     often
    0.11
     smart
    0.11
    POSITIVE LOGITS
     frontera
    0.15
     तहे
    0.14
     آهن
    0.14
    蛲
    0.14
    meshes
    0.14
     consulta
    0.13
     nuevamente
    0.13
    phalodes
    0.13
     rétrécies
    0.13
     plow
    0.13
    Activations Density 0.004%

    No Known Activations