© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14249
    Prev
    Next
    INDEX
    Explanations

    code diffs and code annotations

    oai_token-act-pair · gemini-2.0-flash

    buffer, -

    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
    
    -0.68
    <bos>
    -0.66
    errHandler
    -0.59
    FormTagHelper
    -0.57
    apimachinery
    -0.55
    Diwedd
    -0.55
    +:+
    -0.54
    CppMethod
    -0.52
    %>
    -0.52
    ParallelGroup
    -0.50
    POSITIVE LOGITS
     Exacts
    0.34
     Roskov
    0.32
    fromnode
    0.30
    Absolutely
    0.29
     frattempo
    0.29
     føl
    0.28
     säll
    0.27
    üyor
    0.26
    føl
    0.25
     dieux
    0.25
    Activations Density 3.619%

    No Known Activations