© 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. 3647
    Prev
    Next
    INDEX
    Explanations

    clauses that indicate a state or status has changed over time

    oai_token-act-pair · 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
     then
    -3.86
    then
    -3.45
     Then
    -3.38
    Then
    -3.38
     THEN
    -3.00
    THEN
    -2.83
     entonces
    -2.66
     então
    -2.47
     allora
    -2.31
     سپس
    -2.31
    POSITIVE LOGITS
    expandindo
    0.70
     CreateTagHelper
    0.65
    twimg
    0.49
    しく
    0.49
    anella
    0.46
    avenir
    0.46
    nonatomic
    0.46
    ʺ
    0.44
    дко
    0.43
    ándolos
    0.43
    Activations Density 6.903%

    No Known Activations