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. 4-GEMMASCOPE-TRANSCODER-16K
    4. 7697
    Prev
    Next
    INDEX
    Explanations

    words related to building or rebuilding something

    oai_token-act-pair · gemini-2.0-flash

    structure / construction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    Autoritní
    -0.79
    webElement
    -0.78
    styleType
    -0.71
    +#+#
    -0.70
    antMatchers
    -0.69
    +#+
    -0.66
    OGND
    -0.61
    มาะ
    -0.61
     préfé
    -0.61
    jspx
    -0.61
    POSITIVE LOGITS
     destruction
    0.72
     build
    0.70
    Builder
    0.69
     recre
    0.67
     destru
    0.66
     distru
    0.63
     reconstruction
    0.63
     Zerst
    0.61
     built
    0.60
     recreated
    0.60
    Activations Density 1.908%

    No Known Activations