© 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. 11317
    Prev
    Next
    INDEX
    Explanations

    references to earlier statements or existing work

    oai_token-act-pair · gemini-2.0-flash

    previously

    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
     previously
    -1.16
     previous
    -1.15
     Previously
    -1.13
    previous
    -1.11
    Previously
    -1.10
    previously
    -1.08
     Earlier
    -1.00
     earlier
    -0.99
     Previous
    -0.98
     précédemment
    -0.98
    POSITIVE LOGITS
    WireFormatLite
    0.61
    Portail
    0.55
    WithMany
    0.55
     comparisons
    0.50
     ageing
    0.50
    日閲覧
    0.48
    mapStateToProps
    0.48
     alike
    0.47
     tomorrow
    0.47
    InputBorder
    0.47
    Activations Density 3.722%

    No Known Activations