© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14898
    Prev
    Next
    INDEX
    Explanations

    words related to community service, government, legal proceedings, and military service/duty/personnel

    oai_token-act-pair · gemini-2.0-flash

    serve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     serve
    -1.46
     serving
    -1.42
     served
    -1.41
     serves
    -1.28
    Serving
    -1.25
     Serving
    -1.22
     Serve
    -1.21
    serve
    -1.18
    serving
    -1.17
     SERV
    -1.13
    POSITIVE LOGITS
    +#+#
    1.09
    uxxxx
    1.05
     surla
    1.00
     AssemblyCompany
    1.00
     nakalista
    0.96
     betweenstory
    0.91
    الحياه
    0.90
    matchCondition
    0.86
    发表于
    0.83
    TagMode
    0.83
    Activations Density 38.553%

    No Known Activations