© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10863
    Prev
    Next
    INDEX
    Explanations

    prefixes and suffixes related to medical conditions and treatments

    oai_token-act-pair · gemini-2.0-flash

    anti

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    vacy
    -0.73
    writeFieldEnd
    -0.65
    typeorm
    -0.59
    Espèce
    -0.59
    Autoritní
    -0.57
    notag
    -0.55
     bpy
    -0.55
    ']>;
    -0.55
    ISupport
    -0.54
    RegistryLite
    -0.54
    POSITIVE LOGITS
     disposto
    0.52
     transfieras
    0.51
    RenderAtEndOf
    0.49
    digen
    0.47
     ostavi
    0.44
     Foundry
    0.44
     neurop
    0.43
     parall
    0.43
     tox
    0.43
    hots
    0.42
    Activations Density 0.659%

    No Known Activations