© 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. 12867
    Prev
    Next
    INDEX
    Explanations

    curly braces

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

    latex math symbols and commands, especially those in the "mathrm" context

    oai_token-act-pair · 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
    RegistryLite
    -0.82
    MigrationBuilder
    -0.76
     MessageBoxIcon
    -0.74
    archiviato
    -0.69
     Efq
    -0.69
    UnsafeEnabled
    -0.69
     sumpay
    -0.69
     esternos
    -0.69
     saites
    -0.67
    RUnlock
    -0.66
    POSITIVE LOGITS
    {
    1.37
     {
    1.34
    {
    1.05
     {
    0.96
     {'
    0.87
    {\
    0.86
    {(
    0.85
    {'
    0.85
    {#
    0.84
    {"
    0.83
    Activations Density 0.269%

    No Known Activations