© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 74492
    Prev
    Next
    INDEX
    Explanations

    **stability human objective code ML nuclear event violin strategic in**

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    ˋ
    0.40
    USTER
    0.38
     RESERVE
    0.38
    hereinafter
    0.37
     sayılı
    0.37
     JP
    0.36
     advertisers
    0.36
     ദു
    0.35
    <\/
    0.35
     climbers
    0.34
    POSITIVE LOGITS
     pensamientos
    0.39
     profitable
    0.38
     phenylalanine
    0.38
    profitable
    0.36
    घाटन
    0.35
    reibt
    0.34
    iamy
    0.34
    mai
    0.34
    ုန်
    0.34
     profitably
    0.34
    Activations Density 0.000%

    No Known Activations