© 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. 13417
    Prev
    Next
    INDEX
    Explanations

    words related to classes of limited size

    oai_token-act-pair · gemini-2.0-flash

    multiples of ten

    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
     two
    -0.90
     three
    -0.86
    two
    -0.78
    three
    -0.76
    Three
    -0.74
    Two
    -0.70
     Three
    -0.69
     Two
    -0.68
     deux
    -0.68
     trois
    -0.65
    POSITIVE LOGITS
     Thirty
    1.06
     thirty
    1.05
    Twenty
    1.03
    Thirty
    1.02
     Twenty
    1.00
     forty
    1.00
    Forty
    0.99
     twenty
    0.97
     Forty
    0.96
     fifty
    0.96
    Activations Density 1.829%

    No Known Activations