© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9088
    Prev
    Next
    INDEX
    Explanations

    numbers and some punctuation, often within legal or academic citations or numerical location information

    oai_token-act-pair · gemini-2.0-flash

    8

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Савезне
    -0.54
    Gön
    -0.50
    WithEmail
    -0.50
    DotNetBar
    -0.50
    الثة
    -0.49
     CommonModule
    -0.49
    UrlResolution
    -0.48
     snippetHide
    -0.48
     SqlCommand
    -0.48
    WritableDatabase
    -0.47
    POSITIVE LOGITS
    8
    1.91
     Eight
    1.78
     eight
    1.76
    Eight
    1.52
    ８
    1.45
    eight
    1.45
     Eighth
    1.44
     EIGHT
    1.43
     ocho
    1.41
     eighth
    1.40
    Activations Density 13.663%

    No Known Activations