© 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. 13335
    Prev
    Next
    INDEX
    Explanations

    the word "custody" and words related to legal settings

    oai_token-act-pair · gemini-2.0-flash

    custody

    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
     greateſt
    -0.87
     Majefty
    -0.87
     Houſe
    -0.83
    .}~\
    -0.79
    ^(@)
    -0.79
     Chriftian
    -0.79
     $_"
    -0.77
     Reſ
    -0.77
     ſeveral
    -0.76
     Eſ
    -0.74
    POSITIVE LOGITS
    <bos>
    2.72
    ↵↵
    1.00
    '
    0.96
     the
    0.81
    ↵
    0.79
    ’
    0.78
     and
    0.66
    -
    0.65
    The
    0.63
    H
    0.59
    Activations Density 1.904%

    No Known Activations