© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13050
    Prev
    Next
    INDEX
    Explanations

    words associated with scientific papers and procedures, including dates, genetics, and actions taken.

    oai_token-act-pair · gemini-2.0-flash

    Combining, eliminating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     stessi
    -0.48
     odpově
    -0.45
    abbix
    -0.44
     بالع
    -0.44
     penga
    -0.42
     EconPapers
    -0.42
     gyer
    -0.42
    Achievement
    -0.41
     hason
    -0.41
     montrer
    -0.41
    POSITIVE LOGITS
     TextAppearance
    0.79
     protoimpl
    0.75
    InvalidProtocol
    0.71
    makeConstraints
    0.70
     مشين
    0.65
     AspNetCore
    0.63
    uxxxx
    0.62
    auce
    0.60
     CURIAM
    0.60
    zzleHttp
    0.59
    Activations Density 3.951%

    No Known Activations