© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12648
    Prev
    Next
    INDEX
    Explanations

    instances of arriving, departing or representing, relating to people, objects, and/or data

    oai_token-act-pair · gemini-2.0-flash

    arrive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     arrive
    -2.14
     arrived
    -2.05
     arriving
    -2.03
     arrives
    -1.95
     arrival
    -1.84
    arrive
    -1.77
    arrived
    -1.71
     Arrive
    -1.64
    Arri
    -1.55
     arrivals
    -1.53
    POSITIVE LOGITS
     فريبيس
    0.99
    GraphicsUnit
    0.80
     nahilalakip
    0.77
    ']],
    0.77
    setVerticalGroup
    0.77
    NameInMap
    0.76
    AndEndTag
    0.76
     estekak
    0.75
    fromCharCode
    0.74
    ThroughAttribute
    0.73
    Activations Density 13.723%

    No Known Activations