© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 65025
    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_41_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
     end
    0.70
     infect
    0.70
     Infect
    0.66
     End
    0.54
    端
    0.49
    エンド
    0.48
     paralysie
    0.47
    GENERAL
    0.47
     конца
    0.46
    subcategory
    0.46
    POSITIVE LOGITS
     Sun
    0.43
    Sun
    0.40
     Yat
    0.39
     stimulus
    0.38
    ственности
    0.38
    中山
    0.37
    孙
    0.37
    <%
    0.36
    ِم
    0.36
     stimulating
    0.35
    Activations Density 0.003%

    No Known Activations