© 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. 6113
    Prev
    Next
    INDEX
    Explanations

    snippets of java code related to error messages using Maven and apache-tika

    oai_token-act-pair · gemini-2.0-flash

    technical jargon in code or documentation

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

    code, design, project

    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
    IContainer
    -0.51
     pamamagitan
    -0.46
     possano
    -0.45
     RIPRODUZIONE
    -0.45
     _$
    -0.45
    mongoose
    -0.44
     verkligen
    -0.44
     its
    -0.44
     seventeenth
    -0.44
     forêt
    -0.42
    POSITIVE LOGITS
    IUrlHelper
    0.78
     propOrder
    0.64
     EconPapers
    0.64
     estimés
    0.62
    kloped
    0.60
    CreateModel
    0.59
    wort
    0.59
    XmlAccessorType
    0.58
     postIndex
    0.57
     ligiloj
    0.57
    Activations Density 1.760%

    No Known Activations