© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4956
    Prev
    Next
    INDEX
    Explanations

    a wide range of stopwords and sentence fragments

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     
    -0.73
     with
    -0.71
     the
    -0.71
     B
    -0.65
    <eos>
    -0.64
     to
    -0.63
     of
    -0.63
     D
    -0.62
     and
    -0.62
    ↵↵
    -0.62
    POSITIVE LOGITS
    IntoConstraints
    1.15
     للاسماء
    1.13
    AndEndTag
    1.05
     disambiguazione
    0.99
    MLLoader
    0.98
     Theſe
    0.94
     EconPapers
    0.94
     للمعارف
    0.93
    SharedCtor
    0.91
    featureID
    0.91
    Activations Density 6.594%

    No Known Activations