© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6739
    Prev
    Next
    INDEX
    Explanations

    terms related to laws, trade unions, governments, people, and parliament

    oai_token-act-pair · gemini-2.0-flash

    Law and trade

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     All
    -1.37
     A
    -1.27
     The
    -1.27
     We
    -1.21
     As
    -1.17
     For
    -1.13
     Co
    -1.13
     Re
    -1.11
     I
    -1.10
     In
    -1.10
    POSITIVE LOGITS
     auffi
    1.41
     uſed
    1.32
     raiſ
    1.31
     ſta
    1.29
     myſelf
    1.28
     ainfi
    1.25
     ſtand
    1.24
     étoit
    1.24
     houſe
    1.23
     ſtate
    1.21
    Activations Density 2.090%

    No Known Activations