© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10429
    Prev
    Next
    INDEX
    Explanations

    language related to the sciences, research and funding, particularly in the fields of biology, environment, and technology

    oai_token-act-pair · gemini-2.0-flash

    scientific research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     disambiguazione
    -0.69
    GEBURTSDATUM
    -0.65
     rushes
    -0.57
     rush
    -0.57
    marshaller
    -0.57
    ysław
    -0.56
    ">//
    -0.55
     geslacht
    -0.55
    findpost
    -0.54
     FileReader
    -0.54
    POSITIVE LOGITS
    UseVisualStyle
    0.64
    MigrationBuilder
    0.56
    :+:
    0.56
     المعيارى
    0.55
    ksom
    0.52
    ModelAdmin
    0.51
    achal
    0.46
     behavioral
    0.46
     exaggeration
    0.44
     stem
    0.44
    Activations Density 1.630%

    No Known Activations