© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5872
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs and filler words like "just."

    oai_token-act-pair · gemini-2.0-flash

    just

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     irmã
    -0.48
     programação
    -0.43
     proiz
    -0.41
     offerts
    -0.40
     embalagem
    -0.40
     partenza
    -0.40
    EmptyString
    -0.40
     Flasche
    -0.39
     zircon
    -0.39
     numéros
    -0.39
    POSITIVE LOGITS
     <=",
    1.10
    setVerticalGroup
    1.05
    脚注の使い方
    0.97
    rungsseite
    0.86
     utafitiHapana
    0.85
    AnchorStyles
    0.85
     HasFactory
    0.84
     saites
    0.83
     للمعارف
    0.82
    ioutil
    0.81
    Activations Density 8.215%

    No Known Activations