© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5423
    Prev
    Next
    INDEX
    Explanations

    mentions of international organizations dedicated to health and conservation

    oai_token-act-pair · gemini-2.0-flash

    World

    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
     nsw
    -0.49
     myel
    -0.47
     kub
    -0.46
     prox
    -0.46
    épendance
    -0.45
     treads
    -0.45
     heaters
    -0.45
     arbo
    -0.44
     wipers
    -0.44
    onAttach
    -0.44
    POSITIVE LOGITS
    henswürdigkeiten
    0.72
     varandra
    0.71
    }))
    0.66
     supérieures
    0.66
     supérieurs
    0.66
     européennes
    0.65
     vérit
    0.65
    praš
    0.63
     vectorielles
    0.63
    AddTagHelper
    0.63
    Activations Density 0.509%

    No Known Activations