© 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. 7370
    Prev
    Next
    INDEX
    Explanations

    words related to either computer code or language

    oai_token-act-pair · gemini-2.0-flash

    Code/lists

    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
    </thead>
    -0.54
     تضيفلها
    -0.49
    ktan
    -0.44
    arynge
    -0.42
    Referencie
    -0.41
    ProcessEvent
    -0.40
    ="@
    -0.38
    ătate
    -0.38
    rugada
    -0.37
     поме
    -0.37
    POSITIVE LOGITS
    及其
    0.96
    their
    0.85
     their
    0.84
    とその
    0.81
     ihren
    0.80
    Their
    0.79
     ihrem
    0.77
     EconPapers
    0.77
     accompanied
    0.75
     Their
    0.74
    Activations Density 2.655%

    No Known Activations