© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15043
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to scientific studies and academic papers

    oai_token-act-pair · gemini-2.0-flash

    contains/includes

    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
     Huey
    -0.63
     femininas
    -0.57
     rumahnya
    -0.56
     estekak
    -0.56
     Krakowie
    -0.53
    Diwedd
    -0.52
     beginnetje
    -0.51
     foncé
    -0.51
     bēr
    -0.51
    neros
    -0.50
    POSITIVE LOGITS
     a
    0.75
     an
    0.67
     the
    0.66
    NOPQRST
    0.64
    rabaya
    0.58
     all
    0.57
     SwitchCompat
    0.56
     lots
    0.56
     makl
    0.55
     many
    0.55
    Activations Density 8.592%

    No Known Activations