© 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. 14173
    Prev
    Next
    INDEX
    Explanations

    uses of "that" as a conjunction introducing a subordinate clause expressing a thought or feeling

    oai_token-act-pair · gemini-2.0-flash

    demonstrative pronouns and relative pronouns

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

    that

    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
    Referanser
    -0.54
    way
    -0.54
    ways
    -0.49
     powod
    -0.49
    Pfalz
    -0.49
    ambassade
    -0.48
     manières
    -0.47
    +#+
    -0.46
     måte
    -0.45
     maneras
    -0.45
    POSITIVE LOGITS
     which
    0.81
     this
    0.77
     these
    0.71
     they
    0.63
    setVerticalGroup
    0.61
     those
    0.61
     WHICH
    0.60
    IntoConstraints
    0.60
     you
    0.60
     the
    0.60
    Activations Density 2.117%

    No Known Activations