© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12478
    Prev
    Next
    INDEX
    Explanations

    words with multiple meanings or words that sound similar but are spelled differently

    oai_token-act-pair · gemini-2.0-flash

    French or Spanish snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    transQ
    -0.50
    JsonProperty
    -0.48
    <bos>
    -0.48
     թվական
    -0.48
    rait
    -0.47
     jsonify
    -0.47
     bl
    -0.46
     une
    -0.45
    jing
    -0.45
     Steele
    -0.45
    POSITIVE LOGITS
    expandindo
    1.13
    matchCondition
    0.78
    OGND
    0.75
    IsContent
    0.74
     Biôgrafia
    0.70
     />";
    0.70
    RenderAtEndOf
    0.69
    HostException
    0.68
     useRouter
    0.68
    ConstraintMaker
    0.68
    Activations Density 6.346%

    No Known Activations