© 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. 4869
    Prev
    Next
    INDEX
    Explanations

    articles and prepositions near high-frequency verbs like 'is', 'are', and 'was'

    oai_token-act-pair · gemini-2.0-flash

    to

    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
     kasarigan
    -0.73
    łki
    -0.54
    ांकि
    -0.52
    WebVitals
    -0.50
    AccessorTable
    -0.50
    исленность
    -0.49
    colage
    -0.46
    quias
    -0.46
     AssemblyCompany
    -0.46
     resourceCulture
    -0.45
    POSITIVE LOGITS
     to
    3.44
    to
    1.80
     να
    1.34
    到
    1.29
     To
    1.29
    To
    1.21
     TO
    1.19
    DataTo
    1.16
    tothe
    1.14
     чтобы
    1.04
    Activations Density 15.217%

    No Known Activations