© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 4742
    Prev
    Next
    INDEX
    Explanations

    sentences containing the word "because"

    oai_token-act-pair · gemini-2.0-flash

    because

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    They
    -0.88
    TintMode
    -0.87
     and
    -0.86
     They
    -0.85
     AssemblyProduct
    -0.82
     Either
    -0.81
    Most
    -0.81
     gynhyrchwyd
    -0.81
     Neither
    -0.81
     Most
    -0.76
    POSITIVE LOGITS
     of
    0.90
    ของ
    0.50
     tqdm
    0.47
     của
    0.47
     OF
    0.46
     }^{*}$
    0.43
    ]+=
    0.43
     ของ
    0.40
    VolleyError
    0.38
    ('.');
    0.38
    Activations Density 7.953%

    No Known Activations