© 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. 194749
    Prev
    Next
    INDEX
    Explanations

    foreign sounds

    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
    Horn
    0.41
    ानिस्तान
    0.40
     Carm
    0.40
    ರಿಯ
    0.39
    saf
    0.38
    Ⅺ
    0.37
     Horn
    0.37
     Kiel
    0.37
    蒹
    0.36
     horn
    0.36
    POSITIVE LOGITS
    poque
    0.42
     aiz
    0.41
    hbar
    0.40
    േഷന്‍
    0.39
    ռ
    0.38
    fl
    0.38
    年も
    0.38
     Shay
    0.38
    anean
    0.38
    aine
    0.38
    Activations Density 0.001%

    No Known Activations