© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4160
    Prev
    Next
    INDEX
    Explanations

    code elements such as "val", "fun", and capitalized words followed by a lowercase word, which are common in programming languages like Kotlin

    oai_token-act-pair · gemini-2.0-flash

    Brackets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     مشين
    -0.63
     للمعارف
    -0.59
    findpost
    -0.56
    
    -0.56
    DBNull
    -0.53
    WidgetItem
    -0.52
    出版年
    -0.50
     []:
    -0.50
     eaten
    -0.49
     Starship
    -0.49
    POSITIVE LOGITS
     {
    1.00
     {
    0.77
     {_
    0.73
     \{
    0.73
    {
    0.72
     block
    0.69
    \{
    0.67
    >{
    0.67
    Block
    0.65
     Block
    0.63
    Activations Density 0.733%

    No Known Activations