© 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. 8450
    Prev
    Next
    INDEX
    Explanations

    the word "key" and related terms in computing contexts (e.g., SSH keys, API keys).

    oai_token-act-pair · gemini-2.0-flash

    keys

    np_max-act · gemini-2.0-flash

    keys

    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
     }}$}
    -1.13
    $")
    -1.10
    ^(@)
    -1.08
    BibitemShut
    -1.05
    .")
    
    -1.04
    bibinfo
    -1.02
    )*/
    -1.02
    $.
    
    -0.99
    ).
    
    -0.98
    ]";
    -0.98
    POSITIVE LOGITS
    k
    0.92
    eng
    0.79
    er
    0.79
    '
    0.77
    j
    0.75
    ing
    0.72
    v
    0.72
    q
    0.71
     تضيفلها
    0.69
    sys
    0.69
    Activations Density 1.895%

    No Known Activations