© 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. 206498
    Prev
    Next
    INDEX
    Explanations

    red carpet event or symbolism

    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
    Not in Any Lists

    No Comments

    Negative Logits
    getID
    0.41
     plutonium
    0.37
    尽
    0.37
     desempenho
    0.36
    盡
    0.36
    ิทธิ์
    0.36
     צי
    0.35
     原子
    0.35
     fós
    0.34
    ސް
    0.34
    POSITIVE LOGITS
     red
    1.28
    red
    1.07
     крас
    1.07
    红
    1.06
     Red
    1.05
     carpet
    1.02
    Red
    1.00
    紅
    1.00
     kırmızı
    0.99
     reds
    0.96
    Activations Density 0.000%

    No Known Activations