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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5885
    Prev
    Next
    INDEX
    Explanations

    legal documents and strings of characters that are often used in code files

    oai_token-act-pair · gemini-2.0-flash

    Code or legal text with markers

    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
     '
    -0.97
     "
    -0.94
    ↵
    -0.93
     ‘
    -0.91
    ↵↵
    -0.91
     “
    -0.89
     «
    -0.81
      
    -0.79
     (
    -0.76
    </h2>
    -0.72
    POSITIVE LOGITS
     myſelf
    1.64
     itſelf
    1.61
     Monfieur
    1.59
     raiſ
    1.56
     Anſ
    1.55
     whoſe
    1.53
     pleaſure
    1.53
     himſelf
    1.50
     themſelves
    1.49
     Theſe
    1.46
    Activations Density 1.698%

    No Known Activations