© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246655
    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_40_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
    aterials
    0.39
     picking
    0.38
     canons
    0.38
    क्रा
    0.37
    臤
    0.37
     working
    0.36
     Spir
    0.36
    ﻼ
    0.36
     Mood
    0.36
     arguments
    0.35
    POSITIVE LOGITS
     സംസ്ഥാന
    0.43
    വ്യ
    0.41
     जाएंगी
    0.41
    ოლოდ
    0.41
     څنګه
    0.40
     ஹைட்
    0.39
     whitelist
    0.39
     სახელმწიფ
    0.39
    initState
    0.39
     Pennsylvania
    0.38
    Activations Density 0.000%

    No Known Activations