© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 254045
    Prev
    Next
    INDEX
    Explanations

    integral

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     more
    0.42
    ಕೆ
    0.37
     более
    0.37
     over
    0.37
     över
    0.36
     angesch
    0.36
    Ghana
    0.35
    ﻐ
    0.35
    Gard
    0.34
    献
    0.34
    POSITIVE LOGITS
     integral
    1.69
    Integral
    1.63
     Integral
    1.62
    integral
    1.56
     integrals
    1.19
     integrale
    1.02
    积分
    0.87
    積分
    0.81
     интегра
    0.78
     INTEGR
    0.75
    Activations Density 0.005%

    No Known Activations