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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13800
    Prev
    Next
    INDEX
    Explanations

    legal or formal verbiage used in contracts or court decisions

    oai_token-act-pair · gemini-2.0-flash

    ever, fore

    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
     up
    -0.95
     Up
    -0.69
     doInBackground
    -0.68
    matchCondition
    -0.68
    setContentView
    -0.65
    CloseOperation
    -0.63
    complexContent
    -0.59
    PhysRevLett
    -0.57
     métallique
    -0.54
    Up
    -0.53
    POSITIVE LOGITS
    ever
    1.00
    fore
    0.85
    EVER
    0.84
     ever
    0.81
    ver
    0.78
    Ever
    0.72
    soever
    0.72
    FORE
    0.71
    VER
    0.71
    fores
    0.66
    Activations Density 1.141%

    No Known Activations