© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 118726
    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_27_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
    泺
    0.38
    আ
    0.37
    الم
    0.37
     إذا
    0.37
     эмоциона
    0.37
    إذا
    0.37
    Scaler
    0.35
    Emotional
    0.34
    ¿
    0.34
     Revisited
    0.34
    POSITIVE LOGITS
    reflect
    0.37
    iour
    0.37
    ゅ
    0.36
     autof
    0.36
    ikti
    0.36
    atenate
    0.35
     ګټ
    0.35
    yphenyl
    0.35
     প্রতিফল
    0.35
     ہوگا۔
    0.35
    Activations Density 0.000%

    No Known Activations