© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9167
    Prev
    Next
    INDEX
    Explanations

    instances of someone or something arriving somewhere

    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_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     arrived
    -2.64
     arrive
    -2.55
     arriving
    -2.42
     arrives
    -2.39
    arrived
    -2.23
     arrival
    -2.17
    arrive
    -2.06
     Arrive
    -1.98
    Arri
    -1.95
     Arrived
    -1.95
    POSITIVE LOGITS
    Tazama
    0.57
     LUMP
    0.53
    #+#
    0.50
     Tant
    0.50
    aree
    0.48
     sẻ
    0.48
    nameof
    0.47
    tivamente
    0.47
    хь
    0.46
    Tant
    0.46
    Activations Density 0.769%

    No Known Activations