© 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. 33366
    Prev
    Next
    INDEX
    Explanations

    sandstorm

    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
    Negative Logits
    ೇನೆ
    0.64
    恜
    0.64
    رويج
    0.62
     Вене
    0.62
     மாசுபாடு
    0.61
    一些
    0.61
    jší
    0.60
    وک
    0.59
    俆
    0.59
     instalación
    0.59
    POSITIVE LOGITS
    ش
    0.67
    นั้น
    0.66
            
    0.59
    ด
    0.59
    <h4>
    0.58
    اس
    0.58
     Cet
    0.57
    ON
    0.54
    will
    0.54
     broadband
    0.54
    Activations Density 0.000%

    No Known Activations