© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14388
    Prev
    Next
    INDEX
    Explanations

    medical research relating to myopia in children and adolescents

    oai_token-act-pair · gemini-2.0-flash

    variations of the term 'screen'

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

    screen

    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
     protoimpl
    -0.55
    ptonshire
    -0.55
    DMETHOD
    -0.49
    Sabah
    -0.49
    Accreditation
    -0.48
     cohomology
    -0.48
    VersionUID
    -0.47
    IActionResult
    -0.46
    ddots
    -0.46
    rlpool
    -0.46
    POSITIVE LOGITS
     screen
    1.02
     screens
    0.94
     SCREEN
    0.86
     Screen
    0.81
     Screens
    0.79
     scre
    0.78
    screen
    0.77
    Screen
    0.75
    creen
    0.75
    SCREEN
    0.73
    Activations Density 1.858%

    No Known Activations