© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 106969
    Prev
    Next
    INDEX
    Explanations

    contrarian / contrasting

    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_2_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
    ۹
    1.98
    i
    1.56
    t
    1.54
    ۳
    1.42
    ৯
    1.41
    ৭
    1.38
    ৩
    1.32
    (
    1.31
    inin
    1.26
    ৮
    1.24
    POSITIVE LOGITS
    า
    1.51
    ı
    1.22
    다
    1.18
     are
    1.13
    س
    1.07
    ú
    1.05
    ıc
    1.02
    1.02
    ils
    1.00
    ا
    1.00
    Activations Density 0.005%

    No Known Activations