© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 101673
    Prev
    Next
    INDEX
    Explanations

    emphasize importance

    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_44_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
    all
    0.44
     멀
    0.37
     untreated
    0.37
    empre
    0.37
    ructures
    0.36
    ities
    0.36
     காட்ட
    0.36
     this
    0.35
    зова
    0.35
     दूर
    0.35
    POSITIVE LOGITS
     workaround
    0.41
    chutz
    0.39
     Вя
    0.38
    폈
    0.38
    ريض
    0.37
    deterministic
    0.37
     atmósfera
    0.37
     قَالَ
    0.36
     फ्लाई
    0.36
     ಸುಬ್ಬ
    0.36
    Activations Density 0.002%

    No Known Activations