© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14649
    Prev
    Next
    INDEX
    Explanations

    words and phrases involving diagnosis of medical conditions, particularly neurological ones.

    oai_token-act-pair · gemini-2.0-flash

    Medical/scientific text

    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
    protoimpl
    -0.70
     thao
    -0.56
    CodedInputStream
    -0.54
    Layout
    -0.50
    entierung
    -0.49
    ך
    -0.48
    vale
    -0.48
     conexão
    -0.47
    setLayout
    -0.47
    LayoutPanel
    -0.47
    POSITIVE LOGITS
     createState
    0.66
     externi
    0.61
     nahilalakip
    0.54
     препратки
    0.54
    DebuggerNonUser
    0.54
     ISNI
    0.53
    canActivate
    0.52
    INGHAM
    0.50
     abducted
    0.50
    Välislingid
    0.50
    Activations Density 2.011%

    No Known Activations