© 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
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 9211
    Prev
    Next
    INDEX
    Explanations

    the word "reading"

    oai_token-act-pair · gemini-2.0-flash

    reading

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     reading
    -1.93
    Reading
    -1.90
     Reading
    -1.84
    reading
    -1.80
     READING
    -1.70
    READING
    -1.49
     readings
    -1.45
     Readings
    -1.27
    Readings
    -1.14
     lectura
    -1.05
    POSITIVE LOGITS
     onAnimation
    0.58
    reportWebVitals
    0.58
    jarige
    0.56
    bukkit
    0.55
    IGraphics
    0.54
    keras
    0.53
    glises
    0.50
     sympy
    0.48
    ========
    0.48
     blijven
    0.47
    Activations Density 0.429%

    No Known Activations