© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14846
    Prev
    Next
    INDEX
    Explanations

    mentions of patients, diseases, and medical studies

    oai_token-act-pair · gemini-2.0-flash

    patients

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     فريبيس
    -0.91
    writeFieldEnd
    -0.88
     الاطلاع
    -0.83
     HasFactory
    -0.81
     كومونز
    -0.80
     '\\;'
    -0.79
    脚注の使い方
    -0.79
    SequentialGroup
    -0.77
     विश्वसनीयता
    -0.77
    SuppressMessage
    -0.76
    POSITIVE LOGITS
     with
    0.47
     Show
    0.47
    Show
    0.41
     show
    0.40
     väli
    0.39
    ǎ
    0.39
    tega
    0.38
     who
    0.37
     skj
    0.37
    ang
    0.37
    Activations Density 3.176%

    No Known Activations