Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14641
    Prev
    Next
    INDEX
    Explanations

    complex sentences discussing societal-level issues and political action

    oai_token-act-pair · gemini-2.0-flash

    motivation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ReusableCell
    -0.81
    TagHelpers
    -0.78
    TagMode
    -0.75
    AddTagHelper
    -0.75
    tagext
    -0.71
    GEBURTSDATUM
    -0.69
    CodeAttribute
    -0.69
    DeleteBehavior
    -0.68
     NSCoder
    -0.67
     lenker
    -0.66
    POSITIVE LOGITS
     motivation
    1.23
     Motivation
    0.95
     motivations
    0.94
     desire
    0.93
    motivation
    0.92
     motiva
    0.91
     incentive
    0.90
    Motivation
    0.88
     motiv
    0.85
     motivated
    0.85
    Activations Density 3.416%

    No Known Activations