© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84067
    Prev
    Next
    INDEX
    Explanations

    UK, US, Stoke, Media, Agile

    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_23_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
    煊
    0.29
    হ্ন
    0.29
    Equ
    0.27
    χεία
    0.27
    IgnoreCase
    0.27
    \\
    0.26
    邛
    0.26
     Dessous
    0.26
    原来
    0.26
    Hydroxy
    0.25
    POSITIVE LOGITS
     各
    0.45
    各
    0.42
     grupos
    0.38
     representan
    0.36
     groups
    0.35
     isso
    0.35
     각
    0.35
     conglomerates
    0.35
     religions
    0.34
     subsidiaries
    0.33
    Activations Density 0.024%

    No Known Activations