© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10128
    Prev
    Next
    INDEX
    Explanations

    family relationships, mostly of women

    oai_token-act-pair · gemini-2.0-flash

    Female names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     guy
    -1.03
     pria
    -0.91
     Mr
    -0.91
     males
    -0.90
    Mr
    -0.89
     mascul
    -0.88
     Mascul
    -0.85
    Males
    -0.85
     lelaki
    -0.85
     mężczy
    -0.85
    POSITIVE LOGITS
     Mary
    0.45
    liese
    0.44
    clientY
    0.43
    teri
    0.43
    LANTA
    0.42
     Julie
    0.41
     Maria
    0.41
    ukone
    0.41
     Marie
    0.41
    UMBIA
    0.40
    Activations Density 7.156%

    No Known Activations