© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 83209
    Prev
    Next
    INDEX
    Explanations

    am

    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_53_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
    Sou
    1.58
     Sou
    1.53
    ソ
    1.50
     ソ
    1.41
     Со
    1.40
    索
    1.29
    Со
    1.27
     sou
    1.24
    sou
    1.23
     सो
    1.16
    POSITIVE LOGITS
    ᠮ
    0.39
     rolled
    0.39
     প্রদেশে
    0.38
     Cata
    0.38
    加以
    0.37
     ಕಟ್ಟ
    0.37
     pregnancy
    0.36
    鹖
    0.36
     Pregnancy
    0.35
     FFT
    0.35
    Activations Density 0.004%

    No Known Activations