© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4459
    Prev
    Next
    INDEX
    Explanations

    phrases in advertisements that target people who are struggling with an issue and want help to solve it

    oai_token-act-pair · gemini-2.0-flash

    the word "then" and its variants

    np_token-act-pair-logits · gpt-4o-mini

    then

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     CreateTagHelper
    -0.75
    ValueGeneration
    -0.64
    ecraft
    -0.52
    bootstrapcdn
    -0.52
    ⓧ
    -0.50
     Вікіпе
    -0.50
    andaag
    -0.49
     pinulongan
    -0.49
     réunis
    -0.49
     lenker
    -0.48
    POSITIVE LOGITS
     then
    1.85
    then
    1.49
     Then
    1.47
    Then
    1.43
     kemudian
    1.31
     THEN
    1.27
    然后
    1.20
     سپس
    1.17
     potem
    1.17
     затем
    1.16
    Activations Density 2.347%

    No Known Activations