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. 13910
    Prev
    Next
    INDEX
    Explanations

    negative opinions on gay rights

    oai_token-act-pair · gemini-2.0-flash

    Design/arts

    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
    usst
    -0.52
     initComponents
    -0.51
     DbType
    -0.50
    SuccessListener
    -0.50
    complexContent
    -0.50
    LayoutPanel
    -0.47
    勿
    -0.47
    AllowUser
    -0.46
    ensement
    -0.46
    NECT
    -0.44
    POSITIVE LOGITS
    tagHelperRunner
    0.72
     textStatus
    0.62
     Melrose
    0.62
    mtrl
    0.62
     Bauhaus
    0.59
     designer
    0.58
     arts
    0.58
     Pride
    0.57
     cabaret
    0.57
    Design
    0.56
    Activations Density 1.698%

    No Known Activations