© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3444
    Prev
    Next
    INDEX
    Explanations

    descriptions of sports players who have suffered injuries and are recovering

    oai_token-act-pair · gemini-2.0-flash

    Injuries

    np_max-act-logits · gemini-2.0-flash

    medical terms related to knee injuries

    np_token-act-pair-logits · gpt-4o-mini
    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
     Levin
    -0.51
     zien
    -0.50
    olische
    -0.49
    zyst
    -0.48
    antar
    -0.46
    BASS
    -0.46
    štu
    -0.46
     navegando
    -0.46
    antina
    -0.45
    anet
    -0.44
    POSITIVE LOGITS
     knee
    1.10
     knees
    1.06
     injury
    1.06
     backs
    1.02
     back
    1.01
     injuries
    0.99
     shoulder
    0.99
     neck
    0.97
     Knee
    0.96
     Injury
    0.94
    Activations Density 2.901%

    No Known Activations