© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10142
    Prev
    Next
    INDEX
    Explanations

    the word "is" or the word "are" modified by any number of adverbs.

    oai_token-act-pair · gemini-2.0-flash

    to be (verb)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     betweenstory
    -0.79
     oprot
    -0.71
    
    -0.65
     termica
    -0.61
     themselves
    -0.61
     Chwiliwch
    -0.60
    FunctionFlags
    -0.60
     kasarigan
    -0.59
    <bos>
    -0.59
    themselves
    -0.58
    POSITIVE LOGITS
    izophrenia
    0.52
     totally
    0.50
     absolutely
    0.49
    kels
    0.47
    ForRow
    0.47
    guez
    0.47
     liquid
    0.46
     مسلم
    0.46
    ندق
    0.46
    тельного
    0.45
    Activations Density 0.779%

    No Known Activations