© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12511
    Prev
    Next
    INDEX
    Explanations

    quantity comparatives

    oai_token-act-pair · gemini-2.0-flash

    more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     more
    -1.91
    More
    -1.45
    more
    -1.45
     More
    -1.39
     MORE
    -1.20
     mehr
    -1.13
    MORE
    -1.05
     więcej
    -1.00
     lebih
    -0.99
    <bos>
    -0.92
    POSITIVE LOGITS
    LookAnd
    0.80
     MainAxisSize
    0.78
     betweenstory
    0.77
    ForRow
    0.67
    InSection
    0.66
    PerformLayout
    0.64
     surla
    0.62
     AssemblyCulture
    0.62
     ProtoMessage
    0.61
     folio
    0.60
    Activations Density 2.897%

    No Known Activations