© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 179867
    Prev
    Next
    INDEX
    Explanations

    silver

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    geois
    0.40
    STEAM
    0.40
     поми
    0.39
     आवर
    0.39
    讃
    0.38
    桶
    0.38
    譚
    0.37
     cracker
    0.36
    ⤷
    0.35
    رائی
    0.35
    POSITIVE LOGITS
     silver
    1.51
    銀
    1.43
     сере
    1.40
     argento
    1.38
    银
    1.35
     argent
    1.34
    silver
    1.33
    Сере
    1.25
     Argent
    1.23
     Silver
    1.23
    Activations Density 0.000%

    No Known Activations