© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12373
    Prev
    Next
    INDEX
    Explanations

    words referring to human genders and sexual situations

    oai_token-act-pair · gemini-2.0-flash

    Males

    np_max-act · gemini-2.0-flash

    men

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109

    men

    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_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    -0.93
     Women
    -0.85
     girls
    -0.82
    Women
    -0.79
     Girls
    -0.75
     WOMEN
    -0.71
     ladies
    -0.71
    women
    -0.69
    Girls
    -0.67
     mujeres
    -0.66
    POSITIVE LOGITS
    脚注の使い方
    0.94
    ContentAsync
    0.82
    UnsafeEnabled
    0.81
     tartalomajánló
    0.78
    SBATCH
    0.78
    -------
    0.77
     كومونز
    0.77
     الحره
    0.76
     LCCN
    0.76
    SequentialGroup
    0.75
    Activations Density 0.483%

    No Known Activations