© 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. 15625
    Prev
    Next
    INDEX
    Explanations

    words related to time, cost, and efficiency

    oai_token-act-pair · gemini-2.0-flash

    Reducing resources

    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
    riwal
    -0.73
    saraba
    -0.66
     OFDb
    -0.64
     typelib
    -0.63
    ValueGeneration
    -0.61
    nologue
    -0.60
     ་་
    -0.59
     $_"
    -0.58
    thâu
    -0.57
     مرئيه
    -0.54
    POSITIVE LOGITS
    httphttps
    0.53
    zeß
    0.49
    glTex
    0.47
    équences
    0.46
    $_['
    0.46
    ينما
    0.44
    mados
    0.43
    basicConfig
    0.43
    참고
    0.43
    acamata
    0.43
    Activations Density 5.489%

    No Known Activations