© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3798
    Prev
    Next
    INDEX
    Explanations

    the word "My" or the prefix "my" in certain contexts

    oai_token-act-pair · gemini-2.0-flash

    occurrences of "My" and "my"

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

    My

    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
     AssemblyProduct
    -0.96
    SourceChecksum
    -0.88
    IntoConstraints
    -0.87
     ExecuteAsync
    -0.85
    WriteTagHelper
    -0.81
    migrationBuilder
    -0.81
    Personensuche
    -0.78
    AndEndTag
    -0.78
     resourceCulture
    -0.72
    sizeCache
    -0.72
    POSITIVE LOGITS
    anos
    0.47
    rm
    0.43
     ex
    0.40
    ona
    0.40
    сей
    0.40
    ost
    0.40
    ex
    0.40
    ato
    0.38
    st
    0.38
    kit
    0.38
    Activations Density 0.589%

    No Known Activations