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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 245360
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_11_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
    圏
    1.19
    س
    1.13
    s
    1.12
    연
    1.11
    ラー
    1.10
    import
    1.09
     पदार्थ
    1.09
    0
    1.08
     целый
    1.08
     cuales
    1.07
    POSITIVE LOGITS
    傊
    1.24
    䀖
    1.23
    țiuni
    1.22
    蒿
    1.22
    देह
    1.21
    কিন্ত
    1.20
    
    1.19
    ட்சத்திர
    1.19
    িশীল
    1.18
     huid
    1.18
    Activations Density 0.000%

    No Known Activations