© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11354
    Prev
    Next
    INDEX
    Explanations

    references to owning an electronic reader or other personal technology, and also references to Kings basketball player Demarcus Cousins joining someone.

    oai_token-act-pair · gemini-2.0-flash

    dust, collecting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     referenties
    -0.67
    IsRequired
    -0.58
    Παραπομπές
    -0.53
    dler
    -0.53
    |^
    -0.52
     continúas
    -0.52
    Tracce
    -0.52
    foria
    -0.50
    getApp
    -0.50
     externi
    -0.50
    POSITIVE LOGITS
     dust
    0.68
    dust
    0.65
    तिहास
    0.63
    :✨
    0.62
     packing
    0.60
     collecting
    0.57
     dusting
    0.57
     collect
    0.56
    Portail
    0.55
     GenerationType
    0.55
    Activations Density 1.538%

    No Known Activations