© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13616
    Prev
    Next
    INDEX
    Explanations

    words, phrases, and numbers related to cost savings and financial information

    oai_token-act-pair · gemini-2.0-flash

    reduction

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    RTGC
    -0.65
     gainera
    -0.63
    tahui
    -0.59
    RegistryLite
    -0.57
    исленность
    -0.56
    webElementXpaths
    -0.55
    space
    -0.54
    Personensuche
    -0.52
    foglal
    -0.52
    省市镇
    -0.52
    POSITIVE LOGITS
     reduction
    0.69
    AndEndTag
    0.66
     reductions
    0.64
     autorytatywna
    0.62
    Reduction
    0.59
     Reduction
    0.58
    reduction
    0.56
     reducing
    0.54
     reduce
    0.53
     REDUCTION
    0.52
    Activations Density 4.169%

    No Known Activations