© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13667
    Prev
    Next
    INDEX
    Explanations

    words related to a sea voyage with diving, exploration, and underseas life

    oai_token-act-pair · gemini-2.0-flash

    ships and harbors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    initComponents
    -0.50
    酬
    -0.45
    roof
    -0.43
    sol
    -0.42
     Susana
    -0.40
    olve
    -0.39
    ühl
    -0.39
     despi
    -0.39
     sol
    -0.39
    uccio
    -0.39
    POSITIVE LOGITS
     anchorage
    0.78
     anchoring
    0.69
     channel
    0.67
     Anch
    0.67
     Spit
    0.66
     Channel
    0.66
     CHANNEL
    0.64
     ویکی‌پدیا
    0.64
     Roskov
    0.64
    inheritDoc
    0.63
    Activations Density 2.503%

    No Known Activations