© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229822
    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_6_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
    ok
    1.09
    ul
    1.07
    est
    1.07
    á
    1.05
    ab
    1.04
    ání
    1.04
    ర్‌
    1.02
     Před
    1.02
    š
    1.02
     هاي
    1.00
    POSITIVE LOGITS
    เป็น
    1.01
    งาม
    0.96
    0.95
     you
    0.93
     espress
    0.92
     repeatability
    0.91
     excision
    0.86
    ੀ
    0.86
    </sub>
    0.86
    ใน
    0.86
    Activations Density 0.000%

    No Known Activations