© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3394
    Prev
    Next
    INDEX
    Explanations

    the word "the" followed by a variety of other words

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    .",
    -0.82
    "},
    -0.75
    ."));
    -0.75
    )";
    -0.72
    setVerticalGroup
    -0.70
    .";
    -0.70
    )։
    -0.67
    Autoritní
    -0.67
     nahilalakip
    -0.66
    intenance
    -0.66
    POSITIVE LOGITS
    Number
    0.66
     Number
    0.62
     number
    0.60
    number
    0.60
    NUMBER
    0.57
     števil
    0.54
     ac
    0.52
     broj
    0.52
    Num
    0.52
    Número
    0.50
    Activations Density 5.093%

    No Known Activations