© 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. 4756
    Prev
    Next
    INDEX
    Explanations

    first person opinions and thoughts about events

    oai_token-act-pair · 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
    sizeCache
    -0.65
    fillType
    -0.63
    NameInMap
    -0.62
    +#+#
    -0.62
    flich
    -0.56
    SpringBootTest
    -0.56
    WriteBarrier
    -0.50
    canestro
    -0.49
    \|_{\
    -0.48
    printStackTrace
    -0.48
    POSITIVE LOGITS
     wouldn
    0.69
    wouldn
    0.59
    BibitemShut
    0.57
    Kaynakça
    0.55
     wouldnt
    0.52
    CHANGE
    0.52
     Would
    0.50
    would
    0.50
     would
    0.50
    alyptus
    0.50
    Activations Density 0.440%

    No Known Activations