© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14149
    Prev
    Next
    INDEX
    Explanations

    mentions of relatives and their ages

    oai_token-act-pair · gemini-2.0-flash

    younger

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     myſelf
    -1.57
     Theſe
    -1.55
     Anſ
    -1.50
     Houſe
    -1.42
     Diſ
    -1.41
     Monfieur
    -1.40
     Reſ
    -1.39
    "):
    -1.39
     itſelf
    -1.38
     Conſ
    -1.37
    POSITIVE LOGITS
    l
    0.88
    ValueStyle
    0.86
    Datuak
    0.85
    <eos>
    0.79
    Slf
    0.78
    Portail
    0.78
    aarrggbb
    0.78
    m
    0.75
    r
    0.74
    n
    0.73
    Activations Density 3.081%

    No Known Activations