© 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. 3611
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to people taking part in something as well as having interest in something

    oai_token-act-pair · gemini-2.0-flash

    say "in"

    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
    IN
    -0.98
     мәкал
    -0.78
     ContentValues
    -0.69
    Personensuche
    -0.69
    RegressionTest
    -0.67
    ніципа
    -0.66
    GEBURTSDATUM
    -0.65
     jScrollPane
    -0.65
     lenker
    -0.64
    fromnode
    -0.64
    POSITIVE LOGITS
     in
    2.00
     dalam
    0.89
    ใน
    0.70
    /*
    0.60
     في
    0.60
     в
    0.59
     în
    0.55
     στην
    0.53
     trong
    0.52
    تقاوى
    0.52
    Activations Density 3.676%

    No Known Activations