© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 30967
    Prev
    Next
    INDEX
    Explanations

    first person

    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_50_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
     बिज
    0.40
     matriz
    0.40
     ganske
    0.39
     bx
    0.39
    amac
    0.37
     मनाने
    0.37
    quierda
    0.37
    zugs
    0.37
     BOY
    0.36
     ぞ
    0.36
    POSITIVE LOGITS
     hope
    1.03
     होप
    1.02
    Hope
    1.01
     Hope
    0.99
    hope
    0.96
     HOPE
    0.89
     hop
    0.87
     Hop
    0.82
     희
    0.82
    希望
    0.82
    Activations Density 0.002%

    No Known Activations