© 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. 4106
    Prev
    Next
    INDEX
    Explanations

    words related to people and relationships between them

    oai_token-act-pair · gemini-2.0-flash

    relative pronouns

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

    relative pronouns

    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
    archiviato
    -0.58
    ندگان
    -0.53
    CppCodeGen
    -0.52
    outez
    -0.49
    nians
    -0.49
    adona
    -0.48
     TextAppearance
    -0.48
     ivelany
    -0.48
    Cartney
    -0.47
    lahraga
    -0.46
    POSITIVE LOGITS
     that
    1.81
     who
    1.61
     which
    1.44
     که
    1.22
     που
    1.18
    that
    1.17
    which
    1.12
    ที่
    1.10
    who
    1.07
     WHICH
    1.04
    Activations Density 2.158%

    No Known Activations