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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7208
    Prev
    Next
    INDEX
    Explanations

    the word "government" and related words such as "council," and "national".

    oai_token-act-pair · gemini-2.0-flash

    government

    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
     and
    -0.64
    帖最后由
    -0.60
    Aktualisiert
    -0.60
     sometimes
    -0.55
     or
    -0.54
    quic
    -0.52
     the
    -0.52
     it
    -0.51
    ick
    -0.51
     what
    -0.49
    POSITIVE LOGITS
    ️
    0.85
    — 
    0.81
     Efq
    0.77
    %)$
    0.73
     scania
    0.72
    WebMethod
    0.71
     piaggio
    0.71
    ')}}"
    0.70
    "):
    
    0.69
    =$("#
    0.68
    Activations Density 2.313%

    No Known Activations