© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4471
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially in PHP, with contextual keywords like 'function', 'return', 'id', 'language', and bracket characters

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with '▁' followed by a capital letter or a specific character

    np_token-act-pair-logits · gpt-4o-mini

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    出版年
    -0.78
     ſtate
    -0.69
     Majefty
    -0.68
     Houſe
    -0.68
    theless
    -0.65
     fubject
    -0.62
     Hift
    -0.62
     itſelf
    -0.61
     greateſt
    -0.60
     Chriftian
    -0.60
    POSITIVE LOGITS
     J
    0.52
     Ba
    0.51
     kur
    0.50
     g
    0.50
     S
    0.50
     dre
    0.49
     f
    0.48
     s
    0.48
     d
    0.47
     T
    0.47
    Activations Density 1.357%

    No Known Activations