© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 145280
    Prev
    Next
    INDEX
    Explanations

    pork tenderloin

    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_18_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
     HEP
    0.47
    題目
    0.45
    ƒ
    0.43
     начин
    0.43
     لح
    0.42
    係
    0.42
    떤
    0.42
     ihan
    0.40
    甙
    0.40
    ↵
    0.40
    POSITIVE LOGITS
     usamos
    0.47
     Immediately
    0.47
    Immediately
    0.43
    это
    0.43
     breached
    0.42
     खींचो
    0.41
     reduzir
    0.41
     berakhir
    0.41
    िखर
    0.40
     realizadas
    0.40
    Activations Density 0.000%

    No Known Activations