© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6795
    Prev
    Next
    INDEX
    Explanations

    the word "bow" or words associated with "bubble gum".

    oai_token-act-pair · gemini-2.0-flash

    bow

    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
    at
    -0.71
     Prehistoric
    -0.68
    ma
    -0.65
     toledo
    -0.61
    for
    -0.60
    all
    -0.59
    index
    -0.58
    in
    -0.57
    first
    -0.55
    2
    -0.55
    POSITIVE LOGITS
    bibinfo
    1.05
    )"),
    0.99
    ']))
    
    0.98
    ']")
    0.96
    ')],
    0.91
    .)}
    0.88
    bibfield
    0.87
    httphttps
    0.86
    )";
    
    0.85
    ')]
    0.85
    Activations Density 1.667%

    No Known Activations