© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6354
    Prev
    Next
    INDEX
    Explanations

    discussions and labels relating to biases in society or statistics

    oai_token-act-pair · gemini-2.0-flash

    terms related to non-heteronormative identities

    np_token-act-pair-logits · gpt-4o-mini

    LGBTQ+ identity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    uxxxx
    -0.66
    writeFieldEnd
    -0.59
    ChildIndex
    -0.57
     Walkover
    -0.55
     culte
    -0.54
    migrationBuilder
    -0.54
     ويكيپيديا
    -0.52
     maîtres
    -0.52
     marrow
    -0.51
    skrä
    -0.50
    POSITIVE LOGITS
     non
    0.78
     Non
    0.71
     bi
    0.68
    saraba
    0.66
    Non
    0.66
     pan
    0.65
     NON
    0.64
     trans
    0.62
    non
    0.62
     Pan
    0.61
    Activations Density 3.237%

    No Known Activations