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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13546
    Prev
    Next
    INDEX
    Explanations

    the word "stationery" and words ending in "eries", as well as words like "gear" and "station."

    oai_token-act-pair · gemini-2.0-flash

    stationery and gear

    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
    setVerticalGroup
    -0.74
     AssemblyCulture
    -0.68
    sidemargin
    -0.64
    ettbewer
    -0.60
    coque
    -0.58
    SBATCH
    -0.57
    obach
    -0.56
    etes
    -0.56
    ically
    -0.55
    roffen
    -0.55
    POSITIVE LOGITS
    stuff
    0.69
     stuff
    0.65
     stuffs
    0.59
     clothing
    0.57
    ArgsConstructor
    0.56
     Stuff
    0.54
    Stuff
    0.54
     accessories
    0.52
     merchandise
    0.50
    ulemon
    0.50
    Activations Density 0.831%

    No Known Activations