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. 7-GEMMASCOPE-TRANSCODER-16K
    4. 7112
    Prev
    Next
    INDEX
    Explanations

    words related to family and lineage, while also activating on CSS code

    oai_token-act-pair · gemini-2.0-flash

    siblings, family

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    İstinadlar
    -0.48
     most
    -0.47
     PeEnEo
    -0.47
    fag
    -0.45
    CONCURRENT
    -0.45
     Eck
    -0.44
     harga
    -0.44
    onymy
    -0.43
     strdup
    -0.43
    Map
    -0.42
    POSITIVE LOGITS
    LookAnd
    0.85
     متعلقه
    0.73
    tagHelperRunner
    0.73
    TagMode
    0.67
    ThroughAttribute
    0.65
    InitVars
    0.63
    MLLoader
    0.59
    رشف
    0.58
    
    0.57
    RTSC
    0.56
    Activations Density 0.624%

    No Known Activations