© 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. 9468
    Prev
    Next
    INDEX
    Explanations

    text where someone is thinking and forming subjective ideas about something

    oai_token-act-pair · gemini-2.0-flash

    think

    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
     myſelf
    -1.16
     himſelf
    -1.02
     Theſe
    -1.00
     raiſ
    -0.96
     تضيفلها
    -0.93
     themſelves
    -0.92
     purpoſe
    -0.91
    BibitemShut
    -0.90
     ſeveral
    -0.90
    duled
    -0.89
    POSITIVE LOGITS
    ↵↵
    0.92
    ↵
    0.88
    <bos>
    0.78
    <eos>
    0.75
    <strong>
    0.71
    ’
    0.69
    ”
    0.63
    <em>
    0.61
    </strong>
    0.60
     “
    0.59
    Activations Density 2.707%

    No Known Activations