© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4460
    Prev
    Next
    INDEX
    Explanations

    internet addresses, computer code and related terminology, especially related to databases

    oai_token-act-pair · gemini-2.0-flash

    networking addresses

    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
    Implications
    -0.49
     weathered
    -0.49
     Guille
    -0.48
     Longevity
    -0.48
     digitized
    -0.46
     asunder
    -0.46
     broadened
    -0.46
     Quint
    -0.45
     plight
    -0.45
     weathering
    -0.45
    POSITIVE LOGITS
     pinulongan
    0.72
    typeorm
    0.61
    eradish
    0.56
    圳
    0.54
     @"/
    0.54
    winston
    0.53
    بوابة
    0.52
    Personensuche
    0.52
    +:+
    0.51
     linkovi
    0.51
    Activations Density 20.573%

    No Known Activations