© 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. 9768
    Prev
    Next
    INDEX
    Explanations

    descriptions of coffee and cafes

    oai_token-act-pair · gemini-2.0-flash

    coffee shops

    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
     تضيفلها
    -0.57
    Hentet
    -0.57
     useState
    -0.52
    protoimpl
    -0.52
     tartalomajánló
    -0.52
     Normdatei
    -0.50
    MeasureSpec
    -0.48
    wyl
    -0.48
     يتيمه
    -0.46
    ogues
    -0.45
    POSITIVE LOGITS
     NDEBUG
    0.60
    UIControlState
    0.59
     betweenstory
    0.55
     patrie
    0.54
     Batteries
    0.53
     Cities
    0.52
     inutile
    0.51
     Италијани
    0.51
    Brains
    0.50
     dịch
    0.49
    Activations Density 1.453%

    No Known Activations