© 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. 9802
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "while" and words that can act as conjunctions.

    oai_token-act-pair · gemini-2.0-flash

    while

    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
    énario
    -0.56
    WireFormatLite
    -0.54
    BeginInit
    -0.53
     später
    -0.53
    <bos>
    -0.51
     et
    -0.50
     papan
    -0.49
     eventually
    -0.49
     infine
    -0.48
     fallen
    -0.48
    POSITIVE LOGITS
     purpoſe
    0.63
     ſtate
    0.59
    шеб
    0.59
     ftate
    0.58
     Cacao
    0.56
     Tapatalk
    0.56
    troppo
    0.55
     Arithmetic
    0.54
     Mero
    0.54
     Diagnosis
    0.54
    Activations Density 1.688%

    No Known Activations