© 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-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16012
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming notation interspersed with natural language.

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
      
    -0.94
       
    -0.57
     […]
    -0.48
    StoreMessageInfo
    -0.48
    ­
    -0.47
     ویکی‌پدی
    -0.43
    prilis
    -0.42
    ！　
    -0.42
     INTERESAR
    -0.42
    </b>
    -0.40
    POSITIVE LOGITS
     
    1.98
    isissez
    0.56
    cessite
    0.53
    ándolos
    0.51
     åren
    0.50
    webtoken
    0.50
    ﹠
    0.50
     #"
    0.49
    ándola
    0.48
    %")
    0.48
    Activations Density 18.614%

    No Known Activations