© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29587
    Prev
    Next
    INDEX
    Explanations

    Earl Grey

    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_10_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
     in
    0.70
    T
    0.68
     Canterbury
    0.64
    poner
    0.59
     देती
    0.59
     Gentlemen
    0.57
     tycker
    0.57
    𝙩
    0.57
    !"
    0.57
     burg
    0.57
    POSITIVE LOGITS
    ä
    0.88
    н
    0.77
    ン
    0.74
    ن
    0.71
    etto
    0.69
    न
    0.66
     ताब
    0.63
    aculate
    0.62
    シ
    0.61
    ain
    0.61
    Activations Density 0.001%

    No Known Activations