© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15847
    Prev
    Next
    INDEX
    Explanations

    code snippets and discussions of text formatting like different fonts

    oai_token-act-pair · gemini-2.0-flash

    code/formal writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Rhestr
    -0.66
    oudoune
    -0.60
    
    -0.58
    Tembelea
    -0.52
    ietic
    -0.51
    kuuta
    -0.51
    #
    -0.50
    ########.
    -0.50
     Insertion
    -0.47
    niająca
    -0.47
    POSITIVE LOGITS
     propOrder
    0.75
     createContext
    0.58
    ItemBackground
    0.54
    richTextPanel
    0.51
    rawDesc
    0.50
    utilisons
    0.49
    rawtypes
    0.49
    parsedMessage
    0.49
    DockStyle
    0.48
    autoIncrement
    0.48
    Activations Density 16.947%

    No Known Activations