© 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. 12948
    Prev
    Next
    INDEX
    Explanations

    sentences that include a comma, a period, and a word indicating a person's title

    oai_token-act-pair · gemini-2.0-flash

    company names and technology-related terms

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

    statements and quotes

    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
    tvguidetime
    -0.64
    Décès
    -0.56
     hjemme
    -0.52
    migrationBuilder
    -0.51
    ("}");
    -0.50
    afficheront
    -0.49
     oreilles
    -0.49
     الرياضيه
    -0.49
     épaules
    -0.49
    iritto
    -0.49
    POSITIVE LOGITS
    tencent
    0.57
    נת
    0.54
    ImageContext
    0.53
    Chat
    0.48
    PILE
    0.48
    twimg
    0.47
     conditionally
    0.47
     Mark
    0.46
    بين
    0.46
    ChildIndex
    0.46
    Activations Density 1.367%

    No Known Activations