© 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
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8519
    Prev
    Next
    INDEX
    Explanations

    the word "though."

    oai_token-act-pair · gemini-2.0-flash

    though

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     though
    -2.23
    though
    -1.91
     THOUGH
    -1.86
    Though
    -1.77
     Though
    -1.74
    <bos>
    -1.62
     tho
    -1.20
     entanto
    -1.07
     however
    -1.01
    however
    -0.97
    POSITIVE LOGITS
    tagHelper
    0.42
     GRAND
    0.39
     قب
    0.39
     medie
    0.38
    grand
    0.38
     co
    0.37
     grand
    0.37
     ratio
    0.36
    ERRA
    0.36
    makeConstraints
    0.36
    Activations Density 0.615%

    No Known Activations