© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10999
    Prev
    Next
    INDEX
    Explanations

    legal and official language, especially in the context of contracts and finances

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act-logits · 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
     both
    -0.55
     an
    -0.53
    kömm
    -0.52
     the
    -0.52
     a
    -0.52
     each
    -0.51
     some
    -0.49
     any
    -0.47
    both
    -0.44
    rimento
    -0.44
    POSITIVE LOGITS
    oredCriteria
    0.84
     EconPapers
    0.73
    WebElementEntity
    0.70
     pleaſure
    0.68
     Himo
    0.68
     pageContext
    0.65
    AsUp
    0.63
     Abonnez
    0.62
    yship
    0.60
    lehem
    0.59
    Activations Density 1.920%

    No Known Activations