© 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. 10148
    Prev
    Next
    INDEX
    Explanations

    words and phrases used in product descriptions, especially relating to clothing and baby products

    oai_token-act-pair · gemini-2.0-flash

    technical terms or properties in programming

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

    technical blog excerpts

    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
     publiques
    -0.60
     család
    -0.52
     publicação
    -0.49
     bisog
    -0.49
    yakarta
    -0.49
     stø
    -0.49
     ço
    -0.49
    LITERATURE
    -0.48
     inférieure
    -0.48
     cérémonie
    -0.47
    POSITIVE LOGITS
    AddTagHelper
    0.84
     estekak
    0.67
    IntoConstraints
    0.66
    ApiModelProperty
    0.65
    oa̍t
    0.62
     AssemblyCompany
    0.61
    styleType
    0.59
    bitField
    0.59
    XmlAccessType
    0.59
     transfieras
    0.58
    Activations Density 2.373%

    No Known Activations