© 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. 9384
    Prev
    Next
    INDEX
    Explanations

    mentions of the first lady and/or of temporal context (like months and uses of 'hand')

    oai_token-act-pair · gemini-2.0-flash

    second-hand goods, first ladies

    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
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -1.09
    ↵↵
    -0.85
    '
    -0.75
    a
    -0.59
    D
    -0.57
    ↵
    -0.57
    1
    -0.56
    A
    -0.56
    -
    -0.56
     "
    -0.55
    POSITIVE LOGITS
     تضيفلها
    0.86
     Theſe
    0.85
     uſed
    0.85
    ℗
    0.85
    ruptedException
    0.85
     numberWith
    0.83
    %)$
    0.80
    XmlAccessType
    0.80
    CloseOperation
    0.79
    tvguidetime
    0.79
    Activations Density 2.144%

    No Known Activations