© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176813
    Prev
    Next
    INDEX
    Explanations

    just in case

    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_20_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
     üç
    0.44
     Garuda
    0.44
     attempts
    0.43
     (!)
    0.43
     ก
    0.43
    ビール
    0.43
     (?)
    0.42
     Ayrıca
    0.42
     consisting
    0.42
    (?)
    0.41
    POSITIVE LOGITS
     पांव
    0.44
    不到
    0.43
    듑
    0.43
     chậm
    0.43
    jav
    0.42
    ialog
    0.42
    sebastian
    0.41
    acept
    0.41
    ૈય
    0.41
    াকের
    0.40
    Activations Density 0.000%

    No Known Activations