© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 133488
    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_50_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
     SSm
    0.34
    ंपूर्वी
    0.31
    Ｓ
    0.30
     saffron
    0.30
    aking
    0.30
     Вас
    0.29
    ্লাম
    0.29
     ইন্ডি
    0.28
     स्टेज
    0.28
     Growing
    0.28
    POSITIVE LOGITS
    খর
    0.35
    홉
    0.35
    ikt
    0.34
     상세
    0.32
    ക്ത
    0.31
    ;#
    0.31
    Klik
    0.31
    JsonObject
    0.31
    Handlers
    0.30
    ρ
    0.30
    Activations Density 0.000%

    No Known Activations