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. 7753
    Prev
    Next
    INDEX
    Explanations

    words or phrases that are being used in an official or formal way

    oai_token-act-pair · gemini-2.0-flash

    is

    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
    AddHtmlAttribute
    -0.59
    Виды
    -0.47
    acara
    -0.47
    tvguidetime
    -0.47
    feitura
    -0.45
    LLocation
    -0.45
    됨
    -0.45
     Wirken
    -0.44
    Franck
    -0.44
     patent
    -0.43
    POSITIVE LOGITS
    >",
    
    0.71
    kháu
    0.69
    __*/
    0.69
    #+#
    0.66
    >");
    
    0.65
     виправивши
    0.65
    parsedMessage
    0.65
     betweenstory
    0.64
    RetentionPolicy
    0.63
    TintMode
    0.63
    Activations Density 37.614%

    No Known Activations