© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5631
    Prev
    Next
    INDEX
    Explanations

    terminology from scientific documents, specifically in the areas of biology, chemistry, and environmental science

    oai_token-act-pair · gemini-2.0-flash

    terms related to biological contaminants

    np_token-act-pair-logits · gpt-4o-mini

    scientific text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     للمعارف
    -0.85
     ujednoznacz
    -0.75
     ProtoMessage
    -0.74
    IUrlHelper
    -0.74
    OGND
    -0.73
    aarrggbb
    -0.71
    expandindo
    -0.71
    醐
    -0.66
    estacks
    -0.65
    MigrationBuilder
    -0.65
    POSITIVE LOGITS
     bio
    0.52
     inputs
    0.49
    Nimbus
    0.47
     point
    0.46
    mobile
    0.46
    inputs
    0.45
     decree
    0.45
     input
    0.44
    térature
    0.44
     Bio
    0.44
    Activations Density 2.354%

    No Known Activations