© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 542
    Prev
    Next
    INDEX
    Explanations

    a mix of words related to electronics, chemistry and law

    oai_token-act-pair · 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
    <bos>
    -0.90
    AccessorTable
    -0.69
    MLLoader
    -0.62
    ябре
    -0.59
     الرياضيه
    -0.57
     noDo
    -0.55
     disambiguazione
    -0.53
    oredCriteria
    -0.53
    adaptiveStyles
    -0.51
    verwijspagina
    -0.51
    POSITIVE LOGITS
    ceptable
    0.62
    icoot
    0.55
     pettico
    0.54
    Rohy
    0.54
     opérateur
    0.53
     Lawn
    0.52
    bouts
    0.52
     ashtray
    0.52
     Nop
    0.52
     bowls
    0.51
    Activations Density 5.987%

    No Known Activations