© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11864
    Prev
    Next
    INDEX
    Explanations

    the word "section" and related terms

    oai_token-act-pair · gemini-2.0-flash

    section

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    section
    -1.83
     section
    -1.49
    sections
    -1.32
     Section
    -1.20
     sections
    -1.19
    Section
    -1.17
     sección
    -1.14
     SECTION
    -1.09
     sezione
    -1.04
     Sections
    -0.99
    POSITIVE LOGITS
     ModelExpression
    0.57
    stdafx
    0.55
    {}{}
    0.47
     BoxDecoration
    0.46
    lars
    0.46
    燮
    0.44
     vortex
    0.44
    已
    0.43
    DataObject
    0.42
    strokeColor
    0.42
    Activations Density 0.322%

    No Known Activations