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. 6764
    Prev
    Next
    INDEX
    Explanations

    words pertaining to vehicles and the automotive market

    oai_token-act-pair · gemini-2.0-flash

    car regulations and governments

    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
     anteriore
    -0.46
     eseguire
    -0.46
    žad
    -0.43
     unmodified
    -0.42
    ugc
    -0.41
    hlung
    -0.41
    江南
    -0.41
     soldati
    -0.41
     fenomeno
    -0.41
     juguetes
    -0.40
    POSITIVE LOGITS
    ISupport
    0.77
    URLException
    0.72
    uxxxx
    0.65
    rizona
    0.63
    ✭✭
    0.60
     Савезне
    0.60
    theless
    0.59
    Expedia
    0.59
    contentLoaded
    0.59
     Affiliations
    0.58
    Activations Density 6.141%

    No Known Activations