© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30366
    Prev
    Next
    INDEX
    Explanations

    tell me

    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_31_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
     please
    0.36
    Bitte
    0.32
    please
    0.32
    してください
    0.31
    してみてください
    0.31
    远处
    0.31
     bitte
    0.30
    ("|"+"
    0.29
    Please
    0.29
     Bitte
    0.29
    POSITIVE LOGITS
    为你
    0.28
     Islamic
    0.27
     Deine
    0.26
    跟你
    0.26
     रह
    0.25
     Lond
    0.25
     Yourself
    0.25
     orchestrated
    0.25
     sle
    0.25
    まして
    0.25
    Activations Density 0.013%

    No Known Activations