© 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. 6010
    Prev
    Next
    INDEX
    Explanations

    sentences describing demographic information about geopolitical locations

    oai_token-act-pair · gemini-2.0-flash

    Census and numerical data

    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
    MemoryWarning
    -0.96
    Билгалдахарш
    -0.87
     itſelf
    -0.82
     Efq
    -0.81
     himſelf
    -0.81
     myſelf
    -0.79
    LookAnd
    -0.78
     becauſe
    -0.77
    writeFieldEnd
    -0.77
    HtmlAttribute
    -0.76
    POSITIVE LOGITS
     W
    0.46
    坞
    0.43
    <bos>
    0.41
     ev
    0.41
     w
    0.40
     kasarigan
    0.39
    ack
    0.39
    cons
    0.39
    W
    0.39
    ev
    0.39
    Activations Density 0.494%

    No Known Activations