© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 213350
    Prev
    Next
    INDEX
    Explanations

    engineering mechanics concepts

    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_47_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
    荳
    0.46
     Acanth
    0.46
     acyl
    0.45
    Draft
    0.43
     Draft
    0.42
    山东
    0.41
     Ac
    0.41
    draft
    0.41
     draft
    0.40
     Суриков
    0.40
    POSITIVE LOGITS
    old
    0.39
    <0xAE>
    0.39
    low
    0.37
    razier
    0.37
    <0xBA>
    0.37
    निर्माण
    0.36
    гия
    0.36
    Bradley
    0.36
    高性能
    0.36
    gradation
    0.35
    Activations Density 0.002%

    No Known Activations