© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14186
    Prev
    Next
    INDEX
    Explanations

    gendered pronouns and words

    oai_token-act-pair · gemini-2.0-flash

    Boys and girls

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     boys
    -2.70
     boy
    -2.53
    Boys
    -2.47
     Boys
    -2.47
    boys
    -2.44
     BOYS
    -2.41
     girls
    -2.34
    boy
    -2.27
     Boy
    -2.25
     girl
    -2.23
    POSITIVE LOGITS
    handleRequest
    0.51
     Alembic
    0.46
     utafitiHapana
    0.46
    <tfoot>
    0.43
     nulle
    0.43
    სქოლიო
    0.41
     acrylique
    0.41
     ActionListener
    0.41
    formik
    0.41
    Naissance
    0.40
    Activations Density 1.927%

    No Known Activations