© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10384
    Prev
    Next
    INDEX
    Explanations

    the word "sat" and words around it describing who or what is sitting, sometimes activating on words describing nearby items and people

    oai_token-act-pair · gemini-2.0-flash

    sat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Efq
    -1.48
     مشين
    -1.45
    InjectAttribute
    -1.39
    WithIOException
    -1.29
     ProtoMessage
    -1.29
     autorytatywna
    -1.29
     myſelf
    -1.28
     '\\;'
    -1.27
    ########.
    -1.25
     feroit
    -1.24
    POSITIVE LOGITS
     
    0.81
     a
    0.77
    and
    0.74
    ,
    0.73
    <strong>
    0.68
    B
    0.67
    n
    0.67
    <i>
    0.66
    .
    0.66
     the
    0.65
    Activations Density 1.028%

    No Known Activations