© 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. 11555
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "be" in various tenses

    oai_token-act-pair · gemini-2.0-flash

    present participles

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

    be

    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
     المعيارى
    -0.63
    MigrationBuilder
    -0.56
     sağlar
    -0.55
     protoimpl
    -0.54
    ^(@)
    -0.54
     prévue
    -0.54
    Хьажоргаш
    -0.52
     atteinte
    -0.52
     jLabel
    -0.50
     gangen
    -0.50
    POSITIVE LOGITS
     making
    1.40
     taking
    1.33
     creating
    1.28
     giving
    1.27
     getting
    1.26
     providing
    1.22
     saying
    1.18
     putting
    1.18
     using
    1.17
     bringing
    1.17
    Activations Density 1.582%

    No Known Activations