© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10662
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with job postings or advertisements, and also words associated with religious beliefs or medical information.

    oai_token-act-pair · gemini-2.0-flash

    say "word-start"

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     fermés
    -0.80
     démocr
    -0.76
     supérieurs
    -0.75
     détru
    -0.75
     hâte
    -0.74
     découver
    -0.74
     dépens
    -0.74
     colorés
    -0.74
     définiti
    -0.73
     étan
    -0.71
    POSITIVE LOGITS
     Económica
    0.31
     Autónoma
    0.27
     spake
    0.27
     houſe
    0.27
     lyre
    0.26
     naps
    0.25
     twain
    0.25
     gallows
    0.25
     remode
    0.25
     jacuzzi
    0.25
    Activations Density 54.797%

    No Known Activations