© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1910
    Prev
    Next
    INDEX
    Explanations

    markers used in legal documents, referring to sections, paragraphs, and cited cases

    oai_token-act-pair · gemini-2.0-flash

    Code and technical documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    Descripció
    -0.57
     Empieza
    -0.54
     AssemblyCulture
    -0.54
    IndentedString
    -0.53
     gainera
    -0.52
     elkaar
    -0.51
    NamedQuery
    -0.50
    bootstrapcdn
    -0.50
    dyž
    -0.50
     transfieras
    -0.50
    POSITIVE LOGITS
    saraba
    0.56
    HtmlAttribute
    0.54
    etCode
    0.53
     [*]
    0.49
    raska
    0.48
     StringTokenizer
    0.47
    ulturen
    0.47
     borracha
    0.47
    enumi
    0.46
    ocide
    0.46
    Activations Density 0.370%

    No Known Activations