© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5326
    Prev
    Next
    INDEX
    Explanations

    text in legal and financial documents including amounts of money, railroad industry, regulatory bodies, and similar context.

    oai_token-act-pair · gemini-2.0-flash

    academic/legal language and abbreviations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    UnknownFieldSet
    -0.50
    cotti
    -0.50
    umbles
    -0.47
    nuts
    -0.45
    fans
    -0.44
    stars
    -0.44
    magic
    -0.43
    rock
    -0.42
    logan
    -0.42
    club
    -0.41
    POSITIVE LOGITS
     purpoſe
    0.65
     Majefty
    0.60
     Efq
    0.57
    UnusedPrivate
    0.55
     Reſ
    0.54
     pleaſure
    0.54
     becauſe
    0.54
     Diſ
    0.52
     reaſon
    0.52
     themſelves
    0.52
    Activations Density 41.648%

    No Known Activations