© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 195970
    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_26_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
     ветер
    0.43
     Дан
    0.43
     ущер
    0.42
    threat
    0.41
     آ
    0.40
    います
    0.39
     اقوام
    0.39
     конфигура
    0.38
    ています
    0.38
     comportamenti
    0.38
    POSITIVE LOGITS
     SFR
    0.46
     Sprint
    0.42
     Alumni
    0.42
     Kre
    0.41
     Times
    0.40
     Legisl
    0.40
     ჯ
    0.40
    쩍
    0.40
     Mirror
    0.39
     Vodafone
    0.39
    Activations Density 0.000%

    No Known Activations