© 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. 2335
    Prev
    Next
    INDEX
    Explanations

    conjunctions used in a conversational manner

    oai_token-act-pair · 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
    /")
    -0.49
    дца
    -0.45
    ceira
    -0.41
    jum
    -0.40
     قب
    -0.40
    codings
    -0.40
    irsi
    -0.39
    RuleContext
    -0.39
    URATION
    -0.39
     pile
    -0.38
    POSITIVE LOGITS
    DoubleQuotes
    0.86
    InjectAttribute
    0.78
    IsContent
    0.77
    ChildScrollView
    0.75
    
    0.74
    
    0.73
    ruptedException
    0.73
     cherchés
    0.71
    SBATCH
    0.67
    ďaka
    0.67
    Activations Density 1.248%

    No Known Activations