© 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. 4417
    Prev
    Next
    INDEX
    Explanations

    proper nouns that start with the letters "S", "L", "C", "R", or "J", sometimes including additional context

    oai_token-act-pair · gemini-2.0-flash

    Random Text

    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
     
    -0.65
     (
    -0.57
    -
    -0.48
    ↵
    -0.47
     S
    -0.41
     C
    -0.41
    e
    -0.40
    p
    -0.40
    i
    -0.39
      
    -0.39
    POSITIVE LOGITS
    GEBURTSDATUM
    1.19
    IUrlHelper
    1.13
    تقاوى
    1.13
    WebElementEntity
    1.13
     Roskov
    1.11
    RenderAtEndOf
    1.09
    rungsseite
    1.09
     nahilalakip
    1.08
     kasarigan
    1.07
     CreateTagHelper
    1.01
    Activations Density 8.505%

    No Known Activations