© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7894
    Prev
    Next
    INDEX
    Explanations

    line breaks that indicate a paragraph or section beginning

    oai_token-act-pair · gemini-2.0-flash

    Technical and legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ↵
    -3.55
      
    -1.77
       
    -1.50
     
    -1.48
     (
    -1.40
        
    -1.35
    ↵↵↵
    -1.34
     I
    -1.25
    -1.23
         
    -1.20
    POSITIVE LOGITS
     Efq
    2.78
     Monfieur
    2.77
     myſelf
    2.69
     Theſe
    2.66
     Jefus
    2.55
     itſelf
    2.53
     $_"
    2.48
     Majefty
    2.47
     Anſ
    2.47
     doubtnut
    2.41
    Activations Density 2.126%

    No Known Activations