© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8045
    Prev
    Next
    INDEX
    Explanations

    the word "down" or "off"

    oai_token-act-pair · gemini-2.0-flash

    down off

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ArgumentParser
    -0.66
     виправивши
    -0.59
    AutoScaleMode
    -0.59
    ups
    -0.59
     ups
    -0.54
    ={({
    -0.54
    וך
    -0.50
    upo
    -0.48
     JpaRepository
    -0.48
    vierung
    -0.46
    POSITIVE LOGITS
    évaluateur
    0.64
    orexia
    0.64
    XmlAccessorType
    0.63
     BoxFit
    0.60
     serata
    0.58
    ومت
    0.58
     joined
    0.58
     placés
    0.58
     romántico
    0.57
     sözler
    0.57
    Activations Density 0.367%

    No Known Activations