© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2566
    Prev
    Next
    INDEX
    Explanations

    words related to sports injuries and medical conditions

    oai_token-act-pair · gemini-2.0-flash

    medical injuries

    np_max-act-logits · gemini-2.0-flash
    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
     joints
    -0.50
     orthopedic
    -0.47
     gesteld
    -0.46
    Ahoj
    -0.46
    InitVars
    -0.45
    braio
    -0.45
     knees
    -0.45
    IMDG
    -0.45
     pernas
    -0.45
    WebServlet
    -0.44
    POSITIVE LOGITS
    ThroughAttribute
    0.78
    aarrggbb
    0.77
    脚注の使い方
    0.73
    \{\\
    0.69
     tore
    0.68
     defaultstate
    0.66
     torn
    0.66
    Captor
    0.66
     men
    0.66
    UserScript
    0.65
    Activations Density 2.841%

    No Known Activations