© 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. 7739
    Prev
    Next
    INDEX
    Explanations

    words associated with tire manufacturing and components

    oai_token-act-pair · gemini-2.0-flash

    rubber and tires

    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
     sej
    -0.53
     Transfer
    -0.50
     transfer
    -0.49
    Transfer
    -0.48
     Transfers
    -0.47
    hant
    -0.46
    onsored
    -0.46
     transfers
    -0.46
    Leaders
    -0.45
    mvp
    -0.45
    POSITIVE LOGITS
     rubber
    0.98
     Rubber
    0.90
     tires
    0.87
     tyres
    0.86
    abestanden
    0.86
    rubber
    0.85
     tyre
    0.84
     Tyre
    0.84
    Rubber
    0.84
     gomma
    0.81
    Activations Density 0.300%

    No Known Activations