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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4429
    Prev
    Next
    INDEX
    Explanations

    mixed sections of code and natural language texts

    oai_token-act-pair · gemini-2.0-flash

    Code/legal text

    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
    SequentialGroup
    -1.29
    tagHelperRunner
    -1.19
    makeConstraints
    -1.07
    rawDesc
    -1.02
    StoreMessageInfo
    -1.02
     snippetHide
    -0.97
    WriteTagHelper
    -0.94
    ConstraintMaker
    -0.93
     cherchés
    -0.91
    styleable
    -0.91
    POSITIVE LOGITS
     
    0.57
    
    0.52
     européennes
    0.51
    一見
    0.48
     sengaja
    0.47
    hasilkan
    0.47
    ssysteme
    0.47
     verksamhet
    0.45
     connues
    0.44
    <sub>
    0.42
    Activations Density 3.091%

    No Known Activations