© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6518
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to plumbing and/or road construction

    oai_token-act-pair · gemini-2.0-flash

    junctions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    didSet
    -0.75
    endpush
    -0.66
    AddTagHelper
    -0.66
    ťaž
    -0.59
    AccessorTable
    -0.52
    CodedInputStream
    -0.51
    StoreMessageInfo
    -0.51
    ksesta
    -0.51
    цездатний
    -0.49
    ække
    -0.48
    POSITIVE LOGITS
     junctions
    0.72
     connectors
    0.68
     junction
    0.68
     connector
    0.65
     join
    0.65
     boundary
    0.61
     exit
    0.60
     Exit
    0.60
     joining
    0.59
    .*")]
    0.59
    Activations Density 2.118%

    No Known Activations