© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8288
    Prev
    Next
    INDEX
    Explanations

    words from multiple languages, including German, French, and English, related to situations, claims and states

    oai_token-act-pair · gemini-2.0-flash

    clauses introducing explanations or reasons

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

    say "that" in different languages

    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
    neros
    -0.53
     GenerationType
    -0.51
    ArrowToggle
    -0.45
    ({},
    -0.44
    ecma
    -0.43
    migrationBuilder
    -0.43
    containsKey
    -0.42
    awtextra
    -0.42
    телю
    -0.41
    rxjs
    -0.41
    POSITIVE LOGITS
     that
    2.70
    that
    1.73
     что
    1.36
     bahwa
    1.34
     że
    1.34
     rằng
    1.34
     dass
    1.31
     که
    1.27
     That
    1.26
     että
    1.23
    Activations Density 1.373%

    No Known Activations