© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11174
    Prev
    Next
    INDEX
    Explanations

    words that might appear in an argument, or words that indicate strong feelings and opinions.

    oai_token-act-pair · gemini-2.0-flash

    conversational, user generated content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Check
    -0.58
     Check
    -0.56
     checks
    -0.50
    ктан
    -0.49
     checked
    -0.48
    hynch
    -0.46
    nost
    -0.46
    Autriche
    -0.46
     Checks
    -0.44
    Dont
    -0.44
    POSITIVE LOGITS
    OrBuilder
    0.87
     незавершена
    0.77
     kidnap
    0.68
    
    0.68
    :✨
    0.68
     disarm
    0.62
    NgModule
    0.62
     edit
    0.61
     ujednoznacz
    0.60
    MigrationBuilder
    0.60
    Activations Density 3.597%

    No Known Activations