© 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. 36582
    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
     Nw
    0.42
     classpath
    0.39
     Bracken
    0.38
    acency
    0.37
     COMPUT
    0.36
    妪
    0.36
     THOMAS
    0.35
     Abelian
    0.35
    แส
    0.35
    Hazel
    0.35
    POSITIVE LOGITS
    rop
    0.40
    ო
    0.38
    ribu
    0.37
    ёнок
    0.36
    من
    0.35
    ru
    0.35
     kivy
    0.34
     k
    0.33
    rup
    0.33
    forKey
    0.33
    Activations Density 0.000%

    No Known Activations