© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12758
    Prev
    Next
    INDEX
    Explanations

    code syntax elements like curly brackets, import statements, class definitions, and constructor methods

    oai_token-act-pair · gemini-2.0-flash

    bracket

    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
     myſelf
    -2.72
     purpoſe
    -2.59
     itſelf
    -2.55
     Efq
    -2.50
     pleaſure
    -2.48
     ſtate
    -2.44
     Majefty
    -2.39
     Monfieur
    -2.39
     himſelf
    -2.36
     themſelves
    -2.33
    POSITIVE LOGITS
    ↵↵
    1.70
     
    1.59
    ↵
    1.36
    (
    1.34
    <strong>
    1.33
    </em>
    1.25
     “
    1.25
      
    1.20
     A
    1.20
    <eos>
    1.17
    Activations Density 0.426%

    No Known Activations