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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10133
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce a statement or fact

    oai_token-act-pair · gemini-2.0-flash

    here

    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
     мы
    -0.31
    我们就
    -0.28
    เรา
    -0.26
     meille
    -0.25
    我們
    -0.25
     lemn
    -0.23
     fossero
    -0.23
     přev
    -0.23
    We
    -0.23
     हमें
    -0.23
    POSITIVE LOGITS
    AutoresizingMask
    0.97
    NOPQRST
    0.84
     незавершена
    0.84
    ValueGeneration
    0.83
    expandindo
    0.83
    最快更新
    0.81
    FailureListener
    0.81
    
    0.79
    WebVitals
    0.77
     AssemblyCompany
    0.75
    Activations Density 27.048%

    No Known Activations