© 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. 4088
    Prev
    Next
    INDEX
    Explanations

    mentions of people, especially women and men

    oai_token-act-pair · gemini-2.0-flash

    woman

    np_max-act · gemini-2.0-flash

    woman

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     woman
    -1.74
     man
    -1.43
     girl
    -1.30
     guy
    -1.28
    woman
    -1.25
     WOMAN
    -1.22
     Woman
    -1.17
     lady
    -1.14
    Woman
    -1.13
     homem
    -1.12
    POSITIVE LOGITS
    tralight
    0.56
     mouseClicked
    0.54
    ebenarnya
    0.54
     disambiguazione
    0.54
     saites
    0.51
    icali
    0.51
    ttemberg
    0.51
    skrä
    0.50
     CreateTagHelper
    0.49
    ckså
    0.49
    Activations Density 0.495%

    No Known Activations