© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3892
    Prev
    Next
    INDEX
    Explanations

    mentions of physical objects, including food, items, components, and products

    oai_token-act-pair · gemini-2.0-flash

    Items

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     items
    -1.52
     Items
    -1.24
     ITEMS
    -1.13
    Items
    -1.11
     goods
    -1.10
    items
    -1.09
     objects
    -1.04
    <bos>
    -1.03
    ITEMS
    -0.83
     item
    -0.82
    POSITIVE LOGITS
     genomen
    0.50
    beispiel
    0.44
     nhau
    0.44
     finnas
    0.43
    setNome
    0.43
     ronda
    0.42
    trong
    0.42
    tabler
    0.42
    psia
    0.42
     réguli
    0.42
    Activations Density 3.655%

    No Known Activations