© 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. 3879
    Prev
    Next
    INDEX
    Explanations

    start and end of code blocks(functions, namespaces, structs/classes, enums, etc)

    oai_token-act-pair · gemini-2.0-flash

    opening curly braces and related constructs

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

    {

    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
    addTab
    -0.57
    슷
    -0.54
    fficio
    -0.50
     ?>/
    -0.50
    }^{*}$
    -0.50
     *}$
    -0.48
    ksis
    -0.47
     \
    -0.46
    </sub>
    -0.46
    '];
    -0.46
    POSITIVE LOGITS
    {
    0.94
     {
    0.88
    {
    0.73
     {(
    0.73
    {_
    0.69
     متعلقه
    0.66
     {.
    0.65
     CreateTagHelper
    0.65
     {,
    0.64
    {(
    0.64
    Activations Density 1.601%

    No Known Activations