© 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. 15660
    Prev
    Next
    INDEX
    Explanations

    verbs related to cooking and recipes, along with numeric measurements.

    oai_token-act-pair · gemini-2.0-flash

    sizes and cutting

    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
     Slice
    -0.68
    didSet
    -0.68
     slice
    -0.63
    glEnable
    -0.60
     <=",
    -0.57
     ролях
    -0.57
     Schicht
    -0.54
    
    -0.53
    Slice
    -0.51
    formik
    -0.50
    POSITIVE LOGITS
     mouth
    0.81
     ویکی‌پدی
    0.75
     si
    0.75
     AssemblyCompany
    0.71
     Mouth
    0.62
     betweenstory
    0.59
    Mouth
    0.58
     sli
    0.57
     بيها
    0.56
    webElementXpaths
    0.56
    Activations Density 5.097%

    No Known Activations