© 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. 11752
    Prev
    Next
    INDEX
    Explanations

    text with high level of formatting for inclusion in legal documents.

    oai_token-act-pair · gemini-2.0-flash

    Opening quotes/parentheses

    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
     they
    -1.32
     that
    -1.23
     you
    -1.21
     for
    -1.20
     which
    -1.19
     there
    -1.18
     but
    -1.16
     we
    -1.15
     if
    -1.15
     this
    -1.14
    POSITIVE LOGITS
    RegressionTest
    0.60
     Waray
    0.57
    httphttps
    0.52
     müſſen
    0.50
    /*---
    0.49
    argout
    0.47
     nakalista
    0.47
    #![
    0.47
     anún
    0.47
     Baillargeon
    0.47
    Activations Density 4.021%

    No Known Activations