© 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. 3847
    Prev
    Next
    INDEX
    Explanations

    what appears to be different types of references such as author names, URLs, and scientific names

    oai_token-act-pair · gemini-2.0-flash

    LaTeX commands or syntax

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

    Code/technical jargon

    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
    DebuggerNonUser
    -0.67
    RRect
    -0.63
    oredCriteria
    -0.59
    AsUp
    -0.58
    awtextra
    -0.57
    RegistryLite
    -0.57
    amaño
    -0.56
    InvalidProtocol
    -0.55
    sizeCache
    -0.53
    migrationBuilder
    -0.52
    POSITIVE LOGITS
    TagMode
    0.63
    hrten
    0.51
    lysis
    0.50
    multirow
    0.50
    mommy
    0.49
    bibitem
    0.48
    Abit
    0.47
     Huf
    0.47
    multicolumn
    0.47
     CreateTagHelper
    0.47
    Activations Density 0.187%

    No Known Activations