© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11476
    Prev
    Next
    INDEX
    Explanations

    hyphenated numbers with digits 1 through 9

    oai_token-act-pair · gemini-2.0-flash

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    <bos>
    -0.62
    KommentareTeilen
    -0.56
    kom
    -0.48
     komma
    -0.47
     Lauf
    -0.47
    cluster
    -0.44
    ණ
    -0.43
    book
    -0.43
    DotNet
    -0.43
    multicolumn
    -0.43
    POSITIVE LOGITS
     distanciation
    0.68
    WithIOException
    0.60
     themſelves
    0.55
     preſent
    0.54
     reaſon
    0.54
     ControllerBase
    0.51
    StructEnd
    0.51
     ſeveral
    0.50
     purpoſe
    0.50
    SharedCtor
    0.49
    Activations Density 0.128%

    No Known Activations