© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 135555
    Prev
    Next
    INDEX
    Explanations

    committed to / pleased to / proud to

    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_6_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
    ية
    1.16
    ي
    1.09
     not
    1.05
     we
    0.97
     can
    0.96
     implicated
    0.96
     they
    0.89
     as
    0.88
     captivated
    0.88
     found
    0.88
    POSITIVE LOGITS
    verb
    0.80
    estimators
    0.80
    fine
    0.79
     हथियार
    0.79
    of
    0.78
    輥
    0.77
     प्रश्न
    0.75
    temperatur
    0.74
    भाव
    0.73
    fledged
    0.72
    Activations Density 0.001%

    No Known Activations