© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 200032
    Prev
    Next
    INDEX
    Explanations

    rule with or over

    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_37_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
     Virgo
    0.40
     Ways
    0.40
    フォルダ
    0.39
     Declan
    0.39
     Rule
    0.38
     Berm
    0.38
     minimize
    0.37
    威
    0.37
     Minimize
    0.37
    Ways
    0.36
    POSITIVE LOGITS
     riserv
    0.40
    |\
    0.39
    overset
    0.38
    璃
    0.38
    IsValid
    0.37
    ท่า
    0.37
     roomy
    0.37
     candidatos
    0.36
     amused
    0.36
     sumptuous
    0.36
    Activations Density 0.002%

    No Known Activations