© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5874
    Prev
    Next
    INDEX
    Explanations

    the phrase "in the"

    oai_token-act-pair · gemini-2.0-flash

    Legal or code events

    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
     events
    -3.23
     Events
    -3.14
     event
    -3.02
     Event
    -2.94
    Events
    -2.89
    events
    -2.86
    Event
    -2.78
     EVENTS
    -2.77
    event
    -2.72
     EVENT
    -2.67
    POSITIVE LOGITS
     even
    0.64
     nawet
    0.62
     sogar
    0.60
     chiar
    0.56
     навіть
    0.52
     bahkan
    0.52
     Bahkan
    0.52
     даже
    0.52
     persino
    0.51
     dokonce
    0.50
    Activations Density 1.591%

    No Known Activations