© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2783
    Prev
    Next
    INDEX
    Explanations

    mentions of materials, especially metal and those used in manufacturing.

    oai_token-act-pair · gemini-2.0-flash

    metal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    WebElementEntity
    -0.90
     metal
    -0.76
    Iron
    -0.74
    expandindo
    -0.73
     Metal
    -0.71
     EconPapers
    -0.71
     Iron
    -0.71
     steel
    -0.70
     STEEL
    -0.69
     Steel
    -0.68
    POSITIVE LOGITS
    freopen
    0.59
     Signalez
    0.54
    Zeneca
    0.50
    ække
    0.49
    marino
    0.46
    гія
    0.46
    ảy
    0.44
    ędziesz
    0.43
    rąg
    0.42
    ḥ
    0.42
    Activations Density 6.697%

    No Known Activations