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. 19-GEMMASCOPE-TRANSCODER-16K
    4. 6441
    Prev
    Next
    INDEX
    Explanations

    the word "global" and words related to it or nearby words related to economic issues

    oai_token-act-pair · gemini-2.0-flash

    global

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    CppMethod
    -0.85
     تضيفلها
    -0.57
    Espèce
    -0.55
     onAnimation
    -0.54
    %")
    -0.53
    )];
    
    -0.52
    InputBorder
    -0.51
    CppCodeGen
    -0.51
    numerusform
    -0.49
    ")]
    
    -0.49
    POSITIVE LOGITS
    /**
    0.55
    mobileqq
    0.55
     الواقع
    0.49
    Spoljašnje
    0.49
    الإنجليزية
    0.49
    istocene
    0.48
     보고
    0.48
    ficamente
    0.48
     pasado
    0.47
    Personendaten
    0.47
    Activations Density 3.530%

    No Known Activations