© 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. 6986
    Prev
    Next
    INDEX
    Explanations

    words related to chemical or pharmaceutical formulations and substances

    oai_token-act-pair · gemini-2.0-flash

    chemical compositions and studies

    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
    adpleegd
    -0.60
    saraba
    -0.55
    Acest
    -0.54
    ✭✭
    -0.53
     protoimpl
    -0.51
    detective
    -0.51
    protoimpl
    -0.50
     detective
    -0.49
     collè
    -0.48
    reportWebVitals
    -0.48
    POSITIVE LOGITS
    érieures
    0.50
    öhe
    0.48
    AxisAlignment
    0.47
    anmar
    0.46
     fresh
    0.45
    ắt
    0.45
     symbols
    0.44
    )}}{
    0.44
     chief
    0.44
     sewing
    0.44
    Activations Density 2.778%

    No Known Activations