© 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. 22-GEMMASCOPE-TRANSCODER-16K
    4. 9683
    Prev
    Next
    INDEX
    Explanations

    words that are used to describe the journey or an action to get somewhere

    oai_token-act-pair · 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
     للمعارف
    -0.87
    ">//
    -0.85
     urbanas
    -0.66
     nahilalakip
    -0.63
     autorytatywna
    -0.62
    GEBURTSDATUM
    -0.62
    VersionUID
    -0.60
    mybatisplus
    -0.59
     publiques
    -0.58
     preguntó
    -0.58
    POSITIVE LOGITS
     tap
    0.70
     channel
    0.68
     Tap
    0.60
     height
    0.59
     Height
    0.54
    height
    0.54
     tapping
    0.54
    ]]
    
    0.53
     taps
    0.53
     CHANNEL
    0.52
    Activations Density 1.875%

    No Known Activations