© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6639
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to gender and discrimination

    oai_token-act-pair · gemini-2.0-flash

    gender

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    GEBURTSDATUM
    -0.79
    HtmlAttribute
    -0.69
    Hozzáférés
    -0.69
    principalTable
    -0.66
    OrWhiteSpace
    -0.64
    djangoproject
    -0.64
    StoryboardSegue
    -0.64
    ParallelGroup
    -0.63
    InjectAttribute
    -0.62
    TagMode
    -0.61
    POSITIVE LOGITS
    +:+
    0.61
    jspx
    0.58
    LoadScene
    0.44
     role
    0.43
    AndroidJUnit
    0.43
     wall
    0.42
     kapcsolat
    0.42
    ───
    0.41
    esModule
    0.41
     Wall
    0.41
    Activations Density 0.900%

    No Known Activations