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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10171
    Prev
    Next
    INDEX
    Explanations

    @ YouTube channel links

    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_13_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
    т
    0.72
    с
    0.69
    ά
    0.61
    س
    0.61
    ан
    0.59
    ირ
    0.55
    面積
    0.55
    想
    0.55
     republics
    0.54
    dimensioni
    0.54
    POSITIVE LOGITS
     ให้
    0.66
     możemy
    0.62
     telur
    0.56
     João
    0.55
     canola
    0.55
     сложности
    0.55
     рекомендуется
    0.55
     aos
    0.53
     légèrement
    0.52
     vám
    0.52
    Activations Density 0.007%

    No Known Activations