© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9884
    Prev
    Next
    INDEX
    Explanations

    sentences that contain the words "that" or "think".

    oai_token-act-pair · gemini-2.0-flash

    that

    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
     EconPapers
    -1.05
     Either
    -0.88
    Even
    -0.85
    TypedDataSet
    -0.84
     Even
    -0.84
     AssemblyProduct
    -0.84
     Neither
    -0.84
     مشين
    -0.82
     When
    -0.82
     Regardless
    -0.81
    POSITIVE LOGITS
    ’
    0.71
    '
    0.65
     is
    0.39
    lungen
    0.38
    kuu
    0.37
     гг
    0.37
    ´
    0.36
    Referințe
    0.34
     by
    0.33
     Leroy
    0.33
    Activations Density 10.566%

    No Known Activations