© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40726
    Prev
    Next
    INDEX
    Explanations

    numbers ending in teen or ty

    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_3_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
     l
    1.07
     a
    0.95
     to
    0.95
     y
    0.84
     o
    0.83
     d
    0.80
     s
    0.79
     b
    0.77
     is
    0.76
     v
    0.75
    POSITIVE LOGITS
    0
    0.73
    )*
    0.70
     жовт
    0.69
    bindingFields
    0.68
    hibition
    0.67
    thed
    0.66
    careous
    0.65
     superflu
    0.64
     développé
    0.64
    DebuggingMode
    0.64
    Activations Density 0.006%

    No Known Activations