Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13404
    Prev
    Next
    INDEX
    Explanations

    a combination of some English words seemingly related to political subjects or personal names, and some non-English words or abbreviations

    oai_token-act-pair · gemini-2.0-flash

    Martin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    Martin
    -0.53
     Martin
    -0.52
    rec
    -0.52
    Rec
    -0.49
     ©️
    -0.47
     rec
    -0.46
     Wikimedijinoj
    -0.44
     martin
    -0.43
     juice
    -0.42
    rek
    -0.42
    POSITIVE LOGITS
    thasone
    0.72
    webElementXpaths
    0.71
    localctx
    0.69
     ویکی‌پدیا
    0.65
    __':
    0.65
    uests
    0.63
    __":
    0.63
    aronder
    0.62
    principalTable
    0.62
    */),
    0.62
    Activations Density 16.764%

    No Known Activations