© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6029
    Prev
    Next
    INDEX
    Explanations

    clauses where someone is being controlled or passed on to another person.

    oai_token-act-pair · gemini-2.0-flash

    selling

    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
    addGap
    -0.47
     Pue
    -0.47
     Spec
    -0.47
    CodedInputStream
    -0.46
    msgTypes
    -0.43
    aulted
    -0.43
    RequestQueue
    -0.41
    quiagem
    -0.40
     dolci
    -0.40
    endpush
    -0.40
    POSITIVE LOGITS
     sold
    0.81
     sell
    0.79
     Sold
    0.77
    Sold
    0.75
     Sell
    0.74
    sold
    0.72
     sells
    0.71
     betweenstory
    0.69
     vendido
    0.65
     vendu
    0.64
    Activations Density 0.837%

    No Known Activations