© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10641
    Prev
    Next
    INDEX
    Explanations

    sentences that describe the negative consequences of city traffic and population density

    oai_token-act-pair · gemini-2.0-flash

    traffic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    enschappe
    -0.54
    меч
    -0.48
     pály
    -0.46
    PreferredItem
    -0.45
    moon
    -0.44
    #+#
    -0.44
    ArrowToggle
    -0.44
    šinou
    -0.44
     ब्रेकडाउन
    -0.44
    +][
    -0.44
    POSITIVE LOGITS
     traffic
    2.25
     Traffic
    1.93
    Traffic
    1.88
    traffic
    1.88
     TRAFFIC
    1.63
     trafic
    1.47
     traffico
    1.44
     tráfico
    1.34
     trafik
    1.33
     traff
    1.21
    Activations Density 1.073%

    No Known Activations