© 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. 10372
    Prev
    Next
    INDEX
    Explanations

    internet addresses and related computer terminology

    oai_token-act-pair · gemini-2.0-flash

    Internet chat log

    np_max-act-logits · gemini-2.0-flash

    French

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     InputDecoration
    -0.77
     Normdatei
    -0.76
     EconPapers
    -0.74
     متعلقه
    -0.73
    InjectAttribute
    -0.72
     فريبيس
    -0.71
    WebVitals
    -0.71
    ArrowToggle
    -0.69
    حياته
    -0.69
    URLException
    -0.68
    POSITIVE LOGITS
     varandra
    0.93
     stället
    0.90
     églises
    0.81
     cérami
    0.79
     dieux
    0.78
     enfans
    0.78
     chrétiens
    0.77
     kysy
    0.77
     démocr
    0.75
     intermédiaire
    0.74
    Activations Density 1.864%

    No Known Activations