© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10303
    Prev
    Next
    INDEX
    Explanations

    phrases related to natural ecosystems and their benefits

    oai_token-act-pair · gemini-2.0-flash

    filter

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ()?;
    -0.50
     GenerationType
    -0.49
    SequentialGroup
    -0.49
    gala
    -0.44
     심
    -0.44
    crat
    -0.43
     henvis
    -0.43
    chrift
    -0.43
    AppName
    -0.43
     stuk
    -0.43
    POSITIVE LOGITS
     filter
    1.09
     FILTER
    1.05
     filters
    1.02
     Filter
    1.00
     filtering
    0.95
    FILTER
    0.94
     buffer
    0.93
     Filters
    0.92
    filter
    0.88
     filtre
    0.88
    Activations Density 3.492%

    No Known Activations