© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 195019
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    Sà
    0.44
     Jackets
    0.40
    boxed
    0.38
    龴
    0.38
    ocysts
    0.36
     ஆய்
    0.36
    ອ
    0.36
    ői
    0.35
     Porém
    0.35
    黐
    0.35
    POSITIVE LOGITS
    ru
    0.45
    ele
    0.43
     Ha
    0.43
    cco
    0.43
    uze
    0.42
    瓜
    0.42
    Ele
    0.41
    rew
    0.41
    eli
    0.39
    ruci
    0.39
    Activations Density 0.000%

    No Known Activations