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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 10995
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to participation in studies, events, or teams

    oai_token-act-pair · gemini-2.0-flash

    suffixes related to participation and enrollment

    np_token-act-pair-logits · gpt-4o-mini

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     useDispatch
    -0.71
     linkovi
    -0.70
    ParallelGroup
    -0.68
     ProtoMessage
    -0.65
    Sklici
    -0.65
     surla
    -0.64
     useRouter
    -0.64
     للاسماء
    -0.62
     Wikispecies
    -0.61
    InjectMocks
    -0.61
    POSITIVE LOGITS
    ver
    0.42
    att
    0.40
    יפ
    0.40
     financieras
    0.39
     Administrativna
    0.39
     lundi
    0.38
     mercredi
    0.38
    Att
    0.37
    deg
    0.37
     avions
    0.37
    Activations Density 1.186%

    No Known Activations