© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 237401
    Prev
    Next
    INDEX
    Explanations

    say "t" words

    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_46_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
    Anal
    0.48
     Anal
    0.47
    anal
    0.42
     anal
    0.41
     analyser
    0.41
     analys
    0.40
     analisis
    0.40
    分析
    0.40
    Analysis
    0.38
    :...
    0.38
    POSITIVE LOGITS
    ondale
    0.38
     приви
    0.38
    TabView
    0.37
     দায়
    0.37
     बाट
    0.37
     dien
    0.36
    Putin
    0.35
     BTU
    0.35
     acts
    0.35
     বাড়
    0.35
    Activations Density 0.003%

    No Known Activations