© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127687
    Prev
    Next
    INDEX
    Explanations

    oregano, orecchiette

    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_3_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
    ك
    1.02
    ви
    0.68
    와의
    0.67
     انت
    0.66
    خ
    0.65
    ル
    0.64
    కు
    0.63
    あ
    0.62
    マ
    0.62
    يق
    0.61
    POSITIVE LOGITS
    ↵↵
    0.68
    .
    0.65
    ار
    0.63
    em
    0.61
    CEP
    0.59
    iv
    0.54
    ate
    0.54
     pudd
    0.54
     😊
    0.53
    ão
    0.52
    Activations Density 0.000%

    No Known Activations