© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6602
    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_39_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
     empirically
    0.39
    ered
    0.38
     Doha
    0.38
    ê
    0.37
    슬
    0.37
     Never
    0.37
    Based
    0.37
    बॉ
    0.37
    ñ
    0.37
     Confederation
    0.37
    POSITIVE LOGITS
    প্তাহ
    0.44
     অপে
    0.40
    鹉
    0.40
    ड्स
    0.39
     '%'
    0.39
     शोभा
    0.36
    醤
    0.36
    ﻁ
    0.35
     excell
    0.35
    ோட
    0.35
    Activations Density 0.000%

    No Known Activations