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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11199
    Prev
    Next
    INDEX
    Explanations

    a mix of computer code, math notation, and biological notation, as well as short words such as "to", "in", "and", "is"

    oai_token-act-pair · gemini-2.0-flash

    code syntax and method calls

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

    Code snippets

    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
    TagHelper
    -0.55
     
    -0.55
     =
    -0.54
     _
    -0.52
    .
    -0.50
    --
    -0.50
     &
    -0.50
     *
    -0.50
    –
    -0.49
    —
    -0.49
    POSITIVE LOGITS
    ".
    
    0.84
     Forumite
    0.83
     мәкал
    0.82
    ?».
    0.80
    Personendaten
    0.78
     bezeichneter
    0.78
     nonUne
    0.77
     IBRARY
    0.76
    `;
    
    0.75
    afficheront
    0.75
    Activations Density 6.730%

    No Known Activations