© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5572
    Prev
    Next
    INDEX
    Explanations

    the word "chair" and related terms, possibly in a context of leadership or furniture

    oai_token-act-pair · gemini-2.0-flash

    chair

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     chair
    -2.83
     Chair
    -2.66
    Chair
    -2.56
    chair
    -2.52
     chairs
    -2.42
     CHAIR
    -2.33
     Chairs
    -2.25
    chairs
    -2.08
    CHAIR
    -2.06
     chairman
    -1.99
    POSITIVE LOGITS
    bootstrapcdn
    0.68
    SpringBootTest
    0.65
    Autoritní
    0.63
    icestershire
    0.63
    djangoproject
    0.62
     referenties
    0.61
    ImageContext
    0.61
    PyErr
    0.60
    enterOuterAlt
    0.59
    igshid
    0.59
    Activations Density 0.343%

    No Known Activations