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. 13595
    Prev
    Next
    INDEX
    Explanations

    words related to modifying processes and technical project-oriented discussion.

    oai_token-act-pair · gemini-2.0-flash

    smooth, wrapped

    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
     smooth
    -0.75
    smooth
    -0.73
     smoothed
    -0.61
     Monitoring
    -0.60
    Smooth
    -0.60
     monitors
    -0.59
    Monitoring
    -0.58
     monitoring
    -0.58
     Smooth
    -0.58
     smoothness
    -0.56
    POSITIVE LOGITS
    MLLoader
    0.77
    LabelTagHelper
    0.71
     NUKAT
    0.68
    XmlEnum
    0.68
    urlopen
    0.66
    LookAnd
    0.64
    OCCURRED
    0.63
    érales
    0.62
    ças
    0.61
    Explicación
    0.61
    Activations Density 15.548%

    No Known Activations