© 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. 14285
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the" when it's preceded by certain words such as "given"

    oai_token-act-pair · gemini-2.0-flash

    phrases emphasizing "the" and contextual descriptors

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

    the

    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
     resté
    -0.46
     bailando
    -0.45
     the
    -0.45
     extérieurs
    -0.42
    PerformLayout
    -0.39
     iaitu
    -0.38
     femminile
    -0.38
     rempliss
    -0.38
    AsUp
    -0.36
     maschile
    -0.36
    POSITIVE LOGITS
     level
    0.82
     fact
    0.80
     ProtoMessage
    0.76
     referenties
    0.75
     nakalista
    0.75
     lack
    0.74
     many
    0.73
     possibility
    0.72
    Билгалдахарш
    0.70
     notion
    0.69
    Activations Density 2.667%

    No Known Activations