© 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. 6613
    Prev
    Next
    INDEX
    Explanations

    code snippets with the word "assembly" and references to memory buffers

    oai_token-act-pair · gemini-2.0-flash

    programming

    np_max-act · gemini-2.0-flash

    assembly

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    
    -1.18
    rungsseite
    -1.15
    脚注の使い方
    -1.12
     AssemblyTitle
    -1.00
     مشين
    -0.98
     تانيه
    -0.97
    DockStyle
    -0.97
    InputBorder
    -0.97
     cherchés
    -0.96
     متعلقه
    -0.95
    POSITIVE LOGITS
     so
    0.71
     long
    0.67
     work
    0.67
     in
    0.66
     "
    0.63
     not
    0.63
     rest
    0.62
     the
    0.60
     sc
    0.60
     pre
    0.59
    Activations Density 0.808%

    No Known Activations