© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5530
    Prev
    Next
    INDEX
    Explanations

    words that are not nouns

    oai_token-act-pair · gemini-2.0-flash

    entities involved in transactions or interactions

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

    Groups of people

    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
     débats
    -0.51
     suivants
    -0.48
    nemia
    -0.46
     encre
    -0.46
     démocr
    -0.45
    FundMe
    -0.45
    izioni
    -0.44
     guerres
    -0.43
     ganda
    -0.43
     vectorielle
    -0.43
    POSITIVE LOGITS
     customers
    1.05
     operators
    1.03
     researchers
    0.99
     practitioners
    0.99
     participants
    0.98
     investors
    0.98
     traders
    0.97
     users
    0.97
     buyers
    0.96
     growers
    0.94
    Activations Density 8.522%

    No Known Activations