© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144373
    Prev
    Next
    INDEX
    Explanations

    how pigs fly

    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_0_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
     on
    1.41
     and
    1.34
     fidèle
    1.09
    on
    1.08
    getVisibility
    0.97
    ጨማሪ
    0.95
    น
    0.94
     or
    0.94
    ség
    0.91
    ફેદ
    0.90
    POSITIVE LOGITS
    '
    1.95
     a
    1.74
    ни
    1.70
    .
    1.55
    り
    1.49
    "
    1.46
    ี
    1.37
    و
    1.27
    ı
    1.22
    า
    1.22
    Activations Density 0.000%

    No Known Activations