© 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. 14365
    Prev
    Next
    INDEX
    Explanations

    sequential or comparative statements

    oai_token-act-pair · gemini-2.0-flash

    then

    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
     mukana
    -0.55
    一是
    -0.48
     sondern
    -0.47
    二是
    -0.46
    kloped
    -0.46
     "..\..\
    -0.46
     acomp
    -0.44
     eventuali
    -0.44
     {(
    -0.43
     amables
    -0.43
    POSITIVE LOGITS
    <bos>
    0.83
    ArgsConstructor
    0.68
     fetchData
    0.63
    addGap
    0.59
     crossorigin
    0.59
    evos
    0.59
    StateException
    0.57
    zeera
    0.57
     Exacts
    0.56
    shed
    0.56
    Activations Density 3.451%

    No Known Activations