© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5081
    Prev
    Next
    INDEX
    Explanations

    discussions of cost and effectiveness

    oai_token-act-pair · gemini-2.0-flash

    cost

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    AndEndTag
    -0.87
     समीक्षक
    -0.83
    StoryboardSegue
    -0.80
     Baillargeon
    -0.77
    
    -0.76
    astify
    -0.75
     AssemblyCulture
    -0.75
    WebServlet
    -0.73
    Diweddarwch
    -0.72
     crossorigin
    -0.71
    POSITIVE LOGITS
     of
    0.52
    nellement
    0.47
     gué
    0.45
    Artículo
    0.43
    fören
    0.42
    ungan
    0.42
    <bos>
    0.41
     száz
    0.40
     thúc
    0.40
    benefit
    0.39
    Activations Density 7.142%

    No Known Activations