© 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. 40638
    Prev
    Next
    INDEX
    Explanations

    amenities and amenable

    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
     of
    0.84
    ي
    0.77
    ě
    0.77
    =");
    0.72
     fitter
    0.70
    ી
    0.69
    ем
    0.68
    。
    0.68
    ಿ
    0.66
     estómago
    0.65
    POSITIVE LOGITS
     Amen
    0.82
     amen
    0.81
     amenities
    0.80
     be
    0.76
    م
    0.73
    upp
    0.71
     Amenities
    0.68
    ure
    0.67
     amenity
    0.66
    Amen
    0.64
    Activations Density 0.006%

    No Known Activations