© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8936
    Prev
    Next
    INDEX
    Explanations

    numbers written with periods and commas, often in lists or equations or as percentages

    oai_token-act-pair · gemini-2.0-flash

    code snippets and measurements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     AUSSI
    -0.38
    utze
    -0.38
     drop
    -0.34
     skole
    -0.34
     Vernon
    -0.34
     Dome
    -0.33
     assets
    -0.33
     battle
    -0.32
     wrench
    -0.32
    walt
    -0.32
    POSITIVE LOGITS
    ResumeLayout
    0.85
     <<<<<<<<<<<<<<
    0.85
    QMetaType
    0.83
     kasarigan
    0.83
    énario
    0.81
     تضيفلها
    0.81
    DoubleQuotes
    0.81
    interopRequire
    0.80
     ModelExpression
    0.77
    MemoryWarning
    0.76
    Activations Density 28.933%

    No Known Activations