© 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. 10554
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "Sec" as in "Section" relating to legal and financial topics

    oai_token-act-pair · gemini-2.0-flash

    references to sections or documents

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

    Sec

    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
     cliquant
    -0.43
     nim
    -0.43
    chner
    -0.42
    estría
    -0.39
    cô
    -0.39
    derung
    -0.38
     piacere
    -0.38
    IGNS
    -0.38
     Jim
    -0.37
    Initialize
    -0.37
    POSITIVE LOGITS
     Normdatei
    0.82
    contentLoaded
    0.78
    OGND
    0.74
    CodedInputStream
    0.73
     Vikipedi
    0.71
     transférez
    0.71
     AssemblyCulture
    0.69
     تضيفلها
    0.67
     pinulongan
    0.67
    ThroughAttribute
    0.66
    Activations Density 0.695%

    No Known Activations