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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13723
    Prev
    Next
    INDEX
    Explanations

    numeric references to figures and tables, and maybe math equations

    oai_token-act-pair · gemini-2.0-flash

    say number 8

    np_max-act-logits · gemini-2.0-flash

    say "8"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    8
    -1.56
     eight
    -1.35
     Eight
    -1.22
     eighth
    -1.16
     Eighth
    -1.15
     huit
    -1.06
     acht
    -1.05
    Eight
    -1.03
     EIGHT
    -1.02
    eight
    -1.00
    POSITIVE LOGITS
    enderror
    0.74
    intios
    0.60
     <<<<<<<<<<<<<<
    0.60
     Савезне
    0.59
    ंदीखरीदारी
    0.58
    AccessorTable
    0.57
    nanoTime
    0.57
     viewDidLoad
    0.56
    تقاوى
    0.54
     doInBackground
    0.54
    Activations Density 3.085%

    No Known Activations