© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126300
    Prev
    Next
    INDEX
    Explanations

    Scott Fitzgerald and other authors

    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
    0.68
    多い
    0.63
    篁
    0.63
    ن
    0.63
    ंनी
    0.62
     ضرور
    0.62
    ۹
    0.59
    kale
    0.59
    การ
    0.58
    不对
    0.57
    POSITIVE LOGITS
     \
    0.64
    mathbf
    0.60
     criticised
    0.55
     clenched
    0.55
    ной
    0.53
     lifted
    0.53
     اكبر
    0.53
     disassembled
    0.53
     மிகப்
    0.52
    ן
    0.52
    Activations Density 0.000%

    No Known Activations