© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10075
    Prev
    Next
    INDEX
    Explanations

    the word "the" preceded by one or two other words

    oai_token-act-pair · gemini-2.0-flash

    the word "way"

    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
     way
    -2.80
    Way
    -2.31
    way
    -2.17
     Way
    -2.14
     WAY
    -2.06
    WAY
    -1.92
     façon
    -1.09
    ウェイ
    -1.05
     manera
    -1.02
     manière
    -0.99
    POSITIVE LOGITS
    AndEndTag
    0.70
    MessageTagHelper
    0.63
    Rüyada
    0.62
    发表于
    0.59
    awtextra
    0.59
    <bos>
    0.57
     pinulongan
    0.55
    Билгалдахарш
    0.55
    ביוגרפיה
    0.54
    twimg
    0.54
    Activations Density 1.650%

    No Known Activations