© 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. 31252
    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
     H
    0.40
    𝙷
    0.40
    〽
    0.37
    RoleId
    0.36
    彥
    0.36
    ıza
    0.36
     Kxf
    0.35
    Hx
    0.35
    ery
    0.35
    জা
    0.35
    POSITIVE LOGITS
     Under
    0.50
     UNDER
    0.48
    Under
    0.48
     Վ
    0.45
     अंडर
    0.45
    under
    0.41
    underwear
    0.40
    メンバー
    0.39
    UNDER
    0.39
    ଲ
    0.39
    Activations Density 0.000%

    No Known Activations