© 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. 14519
    Prev
    Next
    INDEX
    Explanations

    the word "by" and words or phrases commonly associated with it.

    oai_token-act-pair · gemini-2.0-flash

    words indicating a relationship or association

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

    by

    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
     يتيمه
    -0.54
     вони
    -0.43
     for
    -0.43
     in
    -0.43
     Они
    -0.41
     farba
    -0.41
     dirigió
    -0.38
     harán
    -0.38
     saluti
    -0.38
     vœux
    -0.37
    POSITIVE LOGITS
     the
    0.89
    uxxxx
    0.82
    RenderAtEndOf
    0.81
     shoppers
    0.67
    MemoryWarning
    0.67
    \{\\
    0.67
     these
    0.66
     your
    0.65
    ImageContext
    0.65
     those
    0.65
    Activations Density 6.391%

    No Known Activations