© 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. 11891
    Prev
    Next
    INDEX
    Explanations

    code or HTML snippets with related discussions, possibly involving jQuery.

    oai_token-act-pair · gemini-2.0-flash

    Element

    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
     Efq
    -1.02
     Monfieur
    -0.96
     $_"
    -0.96
     CreateTagHelper
    -0.89
     ―――――
    -0.86
     Theſe
    -0.85
     pleaſure
    -0.83
     Cæsar
    -0.83
    )";
    -0.82
    RegressionTest
    -0.82
    POSITIVE LOGITS
     element
    1.16
    Element
    1.07
     elements
    1.04
    element
    1.03
     el
    0.99
     Element
    0.98
     tag
    0.93
     elementi
    0.93
     Elements
    0.91
     dom
    0.91
    Activations Density 3.403%

    No Known Activations