© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11486
    Prev
    Next
    INDEX
    Explanations

    a variety of syntax characters and structural elements such as tags, parentheses, and brackets along with words commonly found in technical documentation or code

    oai_token-act-pair · gemini-2.0-flash

    Technical/Scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    viewDidLoad
    -0.52
     newOwner
    -0.52
    SizeMode
    -0.51
     JScrollPane
    -0.50
    simpleType
    -0.49
    stolen
    -0.48
    Atoi
    -0.47
     Dug
    -0.47
    resizingMask
    -0.47
    itemBuilder
    -0.46
    POSITIVE LOGITS
     econômica
    0.72
    kuuta
    0.68
     financeira
    0.60
    ksikon
    0.59
     houſe
    0.59
     étranger
    0.58
    MigrationBuilder
    0.57
    новништво
    0.57
    참고
    0.57
     quæ
    0.55
    Activations Density 1.063%

    No Known Activations