© 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. 6631
    Prev
    Next
    INDEX
    Explanations

    words associated with people having medical conditions, especially mental disorders like schizophrenia and psychosis

    oai_token-act-pair · gemini-2.0-flash

    references to schizophrenia and related conditions

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

    Health conditions

    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
    UnitTesting
    -0.61
    Rptr
    -0.58
     تانيه
    -0.52
    chymal
    -0.49
    پوش
    -0.49
    jero
    -0.48
    rawDesc
    -0.48
    tainer
    -0.47
    IntoConstraints
    -0.47
     يتيمه
    -0.46
    POSITIVE LOGITS
    __(/*!
    0.82
    CodedInputStream
    0.73
     AssemblyCulture
    0.59
    ьаж
    0.58
    colgroup
    0.57
    ρών
    0.57
     دریافت‌شده
    0.56
     Obtén
    0.55
     Chwiliwch
    0.55
    TProtocol
    0.54
    Activations Density 1.463%

    No Known Activations