© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 238428
    Prev
    Next
    INDEX
    Explanations

    conjunctions and contrasting words

    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_32_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
     internation
    0.38
     internationally
    0.37
     international
    0.36
    国際
    0.36
     കൈ
    0.36
     SSH
    0.35
    គាត់
    0.34
    ɭ
    0.34
     slower
    0.34
     अक
    0.34
    POSITIVE LOGITS
     przyjem
    0.41
    TM
    0.40
     ஏற்பட
    0.38
     Trigger
    0.38
     werden
    0.37
    引发
    0.37
     mogą
    0.37
    tracer
    0.37
     wurden
    0.36
     terwijl
    0.36
    Activations Density 0.002%

    No Known Activations