Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9547
    Prev
    Next
    INDEX
    Explanations

    words related to sailing and the America's Cup.

    oai_token-act-pair · gemini-2.0-flash

    The sea or coding

    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
    ellido
    -0.69
    yntaxException
    -0.63
    Gön
    -0.55
    !*\
    -0.55
    terase
    -0.53
    ChildIndex
    -0.52
    TestTools
    -0.49
    usda
    -0.49
    >(_
    -0.48
    jeh
    -0.48
    POSITIVE LOGITS
    IntoConstraints
    0.71
    expandindo
    0.56
    aarrggbb
    0.56
     utafitiHapana
    0.56
     الحره
    0.53
     الدولى
    0.52
    发表于
    0.52
    BaseActivity
    0.51
     exécu
    0.48
    أل
    0.48
    Activations Density 4.641%

    No Known Activations