© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16121
    Prev
    Next
    INDEX
    Explanations

    the word "task"

    oai_token-act-pair · gemini-2.0-flash

    task

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.23
    ंदीखरीदारी
    -0.70
    webElementXpaths
    -0.70
     متعلقه
    -0.62
     nakalista
    -0.60
    MigrationBuilder
    -0.59
    U
    -0.58
     '\\;'
    -0.58
    bootstrapcdn
    -0.58
    K
    -0.58
    POSITIVE LOGITS
    disambiguation
    0.58
    — 
    0.57
    adeloupe
    0.54
    olesale
    0.54
    verages
    0.54
    ABLO
    0.53
    adalupe
    0.52
    kraine
    0.52
    SaveChangesAsync
    0.51
    sarung
    0.51
    Activations Density 4.204%

    No Known Activations