© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15948
    Prev
    Next
    INDEX
    Explanations

    words and entities referring to gender and pronouns

    oai_token-act-pair · gemini-2.0-flash

    female

    np_max-act · gemini-2.0-flash

    female

    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_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     women
    -1.16
     men
    -1.09
     Women
    -1.02
    Women
    -0.97
     girls
    -0.94
     woman
    -0.94
     WOMEN
    -0.91
     Men
    -0.90
     ladies
    -0.89
     boys
    -0.88
    POSITIVE LOGITS
     صوتيه
    0.79
     وتسجيلات
    0.74
    DockStyle
    0.66
     Paglinawan
    0.65
    ientôt
    0.64
     CGSize
    0.64
    UnsafeEnabled
    0.62
     snippetHide
    0.61
    Referències
    0.60
    ruptedException
    0.60
    Activations Density 20.599%

    No Known Activations