© 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
    2. Gemma-3-27B-IT
    3. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 175914
    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
     уби
    0.39
    貂
    0.39
     Dover
    0.39
    జా
    0.36
     Haf
    0.36
     marker
    0.35
     shov
    0.35
     Jawah
    0.35
     тре
    0.35
    鸽
    0.35
    POSITIVE LOGITS
    ło
    0.39
    intl
    0.38
     IU
    0.37
    ientos
    0.36
     control
    0.36
    iend
    0.36
    owało
    0.36
     Presidents
    0.36
    傊
    0.35
    Control
    0.35
    Activations Density 0.000%

    No Known Activations