© 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. 4371
    Prev
    Next
    INDEX
    Explanations

    a narrative involving a formal process or bureau.

    oai_token-act-pair · gemini-2.0-flash

    customs

    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
    EDEFAULT
    -0.66
    WebServlet
    -0.65
    UnusedPrivate
    -0.61
    jspx
    -0.56
     himo
    -0.56
     internetowa
    -0.53
    NameInMap
    -0.52
    цездатний
    -0.51
    InstrumentedTest
    -0.51
     resourceCulture
    -0.50
    POSITIVE LOGITS
     customs
    1.22
     Customs
    1.10
    Customs
    1.05
     border
    0.99
     check
    0.90
     Border
    0.87
    custom
    0.80
     immigration
    0.80
    checkpoint
    0.80
     checkpoint
    0.78
    Activations Density 0.633%

    No Known Activations