© 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
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12387
    Prev
    Next
    INDEX
    Explanations

    the phrase "power law" in scientific contexts

    oai_token-act-pair · gemini-2.0-flash

    power-law physics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     تانيه
    -1.04
    StoryboardSegue
    -1.02
    Hauptartikel
    -1.01
     الحره
    -0.98
     مرئيه
    -0.97
     defaultstate
    -0.97
     CreateTagHelper
    -0.94
    ImageContext
    -0.92
    UserScript
    -0.92
    ContentAsync
    -0.88
    POSITIVE LOGITS
    <bos>
    0.88
    transform
    0.50
    son
    0.48
     trasform
    0.48
    less
    0.47
    ness
    0.46
    ist
    0.46
    const
    0.43
    ward
    0.43
    драт
    0.42
    Activations Density 0.739%

    No Known Activations