© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14243
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to common practices or time

    oai_token-act-pair · gemini-2.0-flash

    time

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     فريبيس
    -0.69
    Према
    -0.57
     mergeFrom
    -0.52
    DMETHOD
    -0.51
    OGND
    -0.49
     useSelector
    -0.47
    BufferException
    -0.46
     PLWABN
    -0.44
    TintMode
    -0.44
     desem
    -0.43
    POSITIVE LOGITS
     age
    1.95
     time
    1.52
     ages
    1.45
     Age
    1.41
    Time
    1.36
     Time
    1.32
    Age
    1.29
    time
    1.24
     AGE
    1.23
     tried
    1.20
    Activations Density 0.691%

    No Known Activations