© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1102
    Prev
    Next
    INDEX
    Explanations

    words that describe people in familial relationships or domestic roles

    oai_token-act-pair · gemini-2.0-flash

    motherhood

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    withOpacity
    -0.49
    >{@
    -0.48
    хьтан
    -0.46
     w
    -0.45
    AJAS
    -0.44
    BarStyle
    -0.44
     comuniques
    -0.43
     Bulan
    -0.43
    nextDouble
    -0.42
    ieR
    -0.42
    POSITIVE LOGITS
     homemaker
    0.72
     stepmother
    0.61
     समीक्षक
    0.60
     housewife
    0.59
     wife
    0.59
     مشين
    0.59
     CURIAM
    0.58
    ArgsConstructor
    0.56
     housewives
    0.56
     motherhood
    0.55
    Activations Density 1.196%

    No Known Activations