© 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. 11886
    Prev
    Next
    INDEX
    Explanations

    verbs

    oai_token-act-pair · gemini-2.0-flash

    most

    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
    DockStyle
    -1.08
     surla
    -1.03
    principalColumn
    -1.01
     StatefulWidget
    -0.98
     ujednoznacz
    -0.94
    enumi
    -0.91
    ScopeManager
    -0.90
    !*\
    -0.88
    الدراسه
    -0.88
    oneph
    -0.88
    POSITIVE LOGITS
     all
    1.47
     majority
    1.45
     most
    1.26
    大部分
    1.20
    majority
    1.19
     maioria
    1.16
    all
    1.13
     sebagian
    1.11
     mayoría
    1.11
     ALL
    1.11
    Activations Density 4.021%

    No Known Activations