© 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
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 12611
    Prev
    Next
    INDEX
    Explanations

    the word "then"

    oai_token-act-pair · gemini-2.0-flash

    then

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    -0.71
    then
    -0.61
     dermed
    -0.59
     perciò
    -0.59
     entonces
    -0.59
     normaux
    -0.59
     então
    -0.58
     américains
    -0.58
     meanwhile
    -0.57
     européens
    -0.57
    POSITIVE LOGITS
    matchCondition
    0.59
    createServer
    0.56
    )$_
    0.56
    ictus
    0.54
    AuthProvider
    0.53
    Personendaten
    0.53
    ^(@)
    0.52
    ChildScrollView
    0.52
    mappedBy
    0.51
    cellence
    0.51
    Activations Density 0.212%

    No Known Activations