© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2381
    Prev
    Next
    INDEX
    Explanations

    code blocks that appear to be related to javascript

    oai_token-act-pair · gemini-2.0-flash

    opening brackets in code

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

    parentheses

    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
    AsUp
    -0.68
    Jereo
    -0.59
    UnitId
    -0.56
     addSubview
    -0.56
    ValueStyle
    -0.54
    Tä
    -0.53
    قایناق‌لار
    -0.53
    nonatomic
    -0.52
    cahontas
    -0.52
    setViewportView
    -0.50
    POSITIVE LOGITS
     {
    1.09
     {
    0.88
    {
    0.72
    {
    0.72
     {(
    0.71
     $\{
    0.71
     {-
    0.68
    {'
    0.66
     {$
    0.66
     {'
    0.66
    Activations Density 2.244%

    No Known Activations