© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7342
    Prev
    Next
    INDEX
    Explanations

    marks of designation within legal and scientific documents

    oai_token-act-pair · gemini-2.0-flash

    technical patent descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Monfieur
    -0.91
     itſelf
    -0.88
     myſelf
    -0.82
     Jefus
    -0.81
     nonUne
    -0.80
     houſe
    -0.79
     ſeveral
    -0.79
     Majefty
    -0.77
     pleaſure
    -0.77
     ſmall
    -0.76
    POSITIVE LOGITS
     im
    0.45
     I
    0.42
    -
    0.41
     gema
    0.39
    <code>
    0.37
     J
    0.37
     t
    0.37
    PASSED
    0.37
    Except
    0.37
     except
    0.36
    Activations Density 1.825%

    No Known Activations