© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9903
    Prev
    Next
    INDEX
    Explanations

    mentions of birth dates and exhibits

    oai_token-act-pair · gemini-2.0-flash

    born

    np_max-act · gemini-2.0-flash

    born

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     Reſ
    -0.69
     Houſe
    -0.66
     fevere
    -0.63
     ſever
    -0.62
     ſche
    -0.62
     Diſ
    -0.61
     Perſ
    -0.59
     Majefty
    -0.59
     Anſ
    -0.58
     Chriftian
    -0.58
    POSITIVE LOGITS
    <bos>
    1.94
    +#+
    0.73
    sizeCache
    0.71
    Autoritní
    0.71
     the
    0.68
    /**
    0.60
    featureID
    0.53
     a
    0.51
     en
    0.50
    Hauptartikel
    0.50
    Activations Density 3.536%

    No Known Activations