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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11539
    Prev
    Next
    INDEX
    Explanations

    disclaimers or warnings related to potential health problems

    oai_token-act-pair · gemini-2.0-flash

    tokens related to warnings or cautionary messages

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

    Scientific/medical texts

    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
     yerine
    -0.52
     Branch
    -0.48
     *++
    -0.47
     Moonlight
    -0.47
    raszam
    -0.44
     kuu
    -0.44
     backstage
    -0.42
    itäts
    -0.42
     headless
    -0.42
     remembered
    -0.42
    POSITIVE LOGITS
     ModelExpression
    0.63
     estekak
    0.62
     שוליים
    0.58
    PRNewswire
    0.57
    Nazionale
    0.56
    THON
    0.56
    usercontent
    0.55
     kasarigan
    0.55
    demies
    0.54
    قایناقلار
    0.53
    Activations Density 0.697%

    No Known Activations