© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12924
    Prev
    Next
    INDEX
    Explanations

    words associated with creation, changes, and updates.

    oai_token-act-pair · gemini-2.0-flash

    new

    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
     new
    -1.84
    new
    -1.76
    New
    -1.35
    NEW
    -1.33
     NEW
    -1.27
    <bos>
    -1.27
     nuevo
    -1.25
     nueva
    -1.25
     nuevos
    -1.21
     nieuwe
    -1.21
    POSITIVE LOGITS
     resourceCulture
    0.69
     médicale
    0.61
     cytoplasm
    0.57
    ouple
    0.56
     médicaux
    0.55
    enterOuterAlt
    0.54
    SError
    0.54
    ogast
    0.54
    didSet
    0.53
    nhan
    0.53
    Activations Density 3.331%

    No Known Activations