© 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
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 15086
    Prev
    Next
    INDEX
    Explanations

    currency amounts and quantitative mentions

    oai_token-act-pair · gemini-2.0-flash

    millions of dollars

    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
     living
    -1.51
    living
    -1.35
     Living
    -1.31
    Living
    -1.31
     LIVING
    -1.26
    LIVING
    -1.07
     vivant
    -0.91
     live
    -0.81
     alive
    -0.79
     hidup
    -0.76
    POSITIVE LOGITS
     BoxDecoration
    0.56
    phrine
    0.51
    SceneManagement
    0.46
    insatz
    0.46
     referenties
    0.46
     î
    0.46
    atellite
    0.46
     VIAF
    0.46
    Bibliograf
    0.46
    ppelin
    0.45
    Activations Density 1.235%

    No Known Activations