© 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
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5386
    Prev
    Next
    INDEX
    Explanations

    mentions of products that are for sale and place names

    oai_token-act-pair · gemini-2.0-flash

    specific programming terms or concepts

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

    Product marketing and websites

    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
     contextLoads
    -0.70
    reactstrap
    -0.60
    HasIndex
    -0.55
     ExecuteAsync
    -0.51
    المناصب
    -0.49
    adpleegd
    -0.49
    >{@
    -0.48
     defStyleAttr
    -0.48
     picioare
    -0.47
     AssemblyTitle
    -0.47
    POSITIVE LOGITS
    AMPLE
    0.64
    newArrayList
    0.57
    didSet
    0.57
     TEMPLATE
    0.55
    ondissement
    0.54
     Samuels
    0.53
    ագրություններ
    0.53
    ActionResult
    0.53
    argout
    0.53
    peicher
    0.52
    Activations Density 0.891%

    No Known Activations