© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11666
    Prev
    Next
    INDEX
    Explanations

    words related to importance, problems, or analysis

    oai_token-act-pair · gemini-2.0-flash

    programming and technology-related terms

    np_token-act-pair-logits · gpt-4o-mini

    Societal issues

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    quien
    -0.41
     Tôi
    -0.40
    ynos
    -0.40
     Eles
    -0.39
     Footnote
    -0.38
     encre
    -0.37
     crdi
    -0.37
     Quels
    -0.36
     sari
    -0.36
     cuál
    -0.36
    POSITIVE LOGITS
     that
    1.09
     they
    0.91
     pinulongan
    0.90
     '\\;'
    0.90
    RenderAtEndOf
    0.88
    DockStyle
    0.85
    providedIn
    0.85
     autorytatywna
    0.84
    исленность
    0.83
    CppMethod
    0.82
    Activations Density 7.711%

    No Known Activations