© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 8205
    Prev
    Next
    INDEX
    Explanations

    the word "intervention"

    oai_token-act-pair · gemini-2.0-flash

    intervention

    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
    "):
    
    -1.40
    ^(@)
    -1.39
    >\<^
    -1.39
     myſelf
    -1.38
    ]--;
    -1.35
    !")
    
    -1.33
     $_"
    -1.32
    )";
    
    -1.32
    \{\\
    -1.30
    BibitemShut
    -1.30
    POSITIVE LOGITS
    ↵
    0.94
    3
    0.82
    ↵↵
    0.80
    2
    0.78
     of
    0.77
    ,
    0.75
    1
    0.75
     before
    0.72
    4
    0.71
     (
    0.71
    Activations Density 1.905%

    No Known Activations