© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75217
    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_31_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
     terutama
    0.30
    lovepoetry
    0.30
     त्यात
    0.29
    的這個
    0.28
    🍾
    0.28
     هذا
    0.27
    ering
    0.27
    晫
    0.27
     этой
    0.26
    EOL
    0.26
    POSITIVE LOGITS
    тивных
    0.30
     struggle
    0.28
     Análisis
    0.27
     ২৭
    0.26
    险
    0.26
    ALLOW
    0.26
    冠軍
    0.26
     분석
    0.26
     concer
    0.25
    严
    0.25
    Activations Density 0.000%

    No Known Activations