© 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. 7743
    Prev
    Next
    INDEX
    Explanations

    uses of the `assert` keyword and sometime `const` keywords in code

    oai_token-act-pair · gemini-2.0-flash

    assert

    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
    Personensuche
    -0.91
     fusca
    -0.78
    
    -0.73
     célè
    -0.71
    +#+#
    -0.70
     démission
    -0.69
     représ
    -0.67
     dévelo
    -0.66
     Tenta
    -0.66
     mercen
    -0.66
    POSITIVE LOGITS
    encils
    0.71
    
    0.71
    RTLD
    0.70
    ″]
    0.60
     natural
    0.59
     particular
    0.59
     par
    0.57
     non
    0.57
    nEnter
    0.57
     be
    0.56
    Activations Density 2.929%

    No Known Activations