© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12094
    Prev
    Next
    INDEX
    Explanations

    the phrase "way to"

    oai_token-act-pair · gemini-2.0-flash

    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_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    InjectAttribute
    -0.82
    ImageContext
    -0.82
    writeFieldEnd
    -0.80
    WriteBarrier
    -0.80
     Houſe
    -0.79
    InputBorder
    -0.78
     houſe
    -0.76
    eeq
    -0.75
    RTCF
    -0.75
    ="@+
    -0.73
    POSITIVE LOGITS
     to
    1.25
     να
    0.40
     so
    0.39
     into
    0.38
    மை
    0.36
     чтобы
    0.35
     להת
    0.35
    шением
    0.34
    方に
    0.32
     na
    0.32
    Activations Density 0.373%

    No Known Activations