© 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. 6780
    Prev
    Next
    INDEX
    Explanations

    code related to plotting data with matplotlib, especially scatter plots and color mapping

    oai_token-act-pair · gemini-2.0-flash

    words related to data visualization and color mapping

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

    code documentation

    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
    tagHelperRunner
    -1.01
    SourceChecksum
    -0.81
     AssemblyCulture
    -0.80
     protoimpl
    -0.69
     Roskov
    -0.68
    SequentialGroup
    -0.67
    ChildScrollView
    -0.66
    ResponseWriter
    -0.62
    DBNull
    -0.61
    UnknownFieldSet
    -0.61
    POSITIVE LOGITS
    ph
    0.51
    Handles
    0.47
    versaries
    0.47
    XmlAccessType
    0.45
     Steg
    0.45
    اریخ
    0.43
     Gener
    0.43
     handle
    0.42
    олові
    0.41
     poitrine
    0.41
    Activations Density 1.793%

    No Known Activations