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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 295
    Prev
    Next
    INDEX
    Explanations

    mentions of dimensions

    oai_token-act-pair · gemini-2.0-flash

    size

    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
     size
    -1.13
    size
    -1.05
    sized
    -1.02
     Size
    -1.01
     SIZE
    -0.99
     sized
    -0.97
    Size
    -0.91
     Smaller
    -0.88
     sizes
    -0.85
     Larger
    -0.85
    POSITIVE LOGITS
     ComVisible
    0.59
    IVEREF
    0.54
    AsUp
    0.54
     MessageBoxIcon
    0.52
    PMailer
    0.52
    HasIndex
    0.52
     impregn
    0.51
     endorsing
    0.50
    DoubleQuotes
    0.50
    ImageField
    0.50
    Activations Density 23.002%

    No Known Activations