© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11405
    Prev
    Next
    INDEX
    Explanations

    words ending in "ely" or is related to metal rolling, braze-welding and fabrication, or is related to a legal citation

    oai_token-act-pair · gemini-2.0-flash

    rolled metal processing

    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
    anical
    -0.68
    Zunanje
    -0.65
    новниш
    -0.64
     AssemblyVersion
    -0.63
    optarg
    -0.62
    ecutive
    -0.61
    AccessorTable
    -0.60
    ieteur
    -0.60
    graphed
    -0.60
     didReceive
    -0.60
    POSITIVE LOGITS
     steel
    0.85
    Iron
    0.76
     Steel
    0.74
    Steel
    0.74
     Iron
    0.73
     iron
    0.73
     metal
    0.70
     STEEL
    0.67
     metall
    0.67
    steel
    0.67
    Activations Density 0.666%

    No Known Activations