Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1178
    Prev
    Next
    INDEX
    Explanations

    a variety of words related to actions, materials, electronics, food, and time.

    oai_token-act-pair · gemini-2.0-flash

    waiting time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    halb
    -0.44
     kiện
    -0.43
    link
    -0.43
    annotate
    -0.43
     שוליים
    -0.43
    ese
    -0.42
    govina
    -0.40
     vente
    -0.39
    try
    -0.39
     k
    -0.39
    POSITIVE LOGITS
     Efq
    0.84
    UnknownFieldSet
    0.76
     pleaſure
    0.74
     Paglinawan
    0.74
    ftagPool
    0.73
    StructEnd
    0.72
     protoimpl
    0.72
    complexContent
    0.70
    onAttach
    0.70
    drawSprites
    0.70
    Activations Density 14.794%

    No Known Activations