© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 8044
    Prev
    Next
    INDEX
    Explanations

    words related to dog behavior training

    oai_token-act-pair · gemini-2.0-flash

    words related to dog toys

    np_token-act-pair-logits · gpt-4o-mini

    toys, chew

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     doInBackground
    -0.79
    IVEREF
    -0.74
    onViewCreated
    -0.71
    GIVEREF
    -0.67
     tubeless
    -0.66
    RunAsync
    -0.66
    ViewFeatures
    -0.66
    AccessFile
    -0.60
    adpleegd
    -0.60
    ViewImports
    -0.60
    POSITIVE LOGITS
     toys
    0.74
     chew
    0.73
     chewing
    0.72
     toy
    0.71
     Toys
    0.65
    chew
    0.65
     Toy
    0.64
    Toy
    0.64
     che
    0.62
     Che
    0.60
    Activations Density 0.895%

    No Known Activations