© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2262
    Prev
    Next
    INDEX
    Explanations

    mentions about starting something from scratch or rewriting something

    oai_token-act-pair · gemini-2.0-flash

    scratch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     AssemblyCompany
    -0.81
    RUnlock
    -0.72
    <bos>
    -0.71
     étoit
    -0.69
     photolibrary
    -0.68
     auroit
    -0.68
     pouvoit
    -0.67
    Бахар
    -0.67
     impunity
    -0.65
     betweenstory
    -0.65
    POSITIVE LOGITS
     programme
    0.46
     grund
    0.44
    isure
    0.44
     method
    0.44
     meny
    0.43
     реб
    0.43
     sia
    0.42
    por
    0.41
     tot
    0.41
     en
    0.40
    Activations Density 1.369%

    No Known Activations