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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 5203
    Prev
    Next
    INDEX
    Explanations

    the word "eastern" followed by the words "the", "part", and numbers

    oai_token-act-pair · gemini-2.0-flash

    Eastern

    np_max-act · gemini-2.0-flash

    Eastern

    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
    )");
    
    -1.53
    )";
    
    -1.44
    — 
    -1.39
    NUMX
    -1.38
     nahilalakip
    -1.38
    "],
    
    -1.38
    GEBURTSDATUM
    -1.37
    "):
    
    -1.37
    BibitemShut
    -1.36
    "},
    
    -1.35
    POSITIVE LOGITS
    2
    1.02
    1
    1.01
    H
    0.92
    3
    0.90
    5
    0.89
    K
    0.89
    ↵↵
    0.88
    S
    0.86
    4
    0.85
    //
    0.84
    Activations Density 5.075%

    No Known Activations