© 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. 8195
    Prev
    Next
    INDEX
    Explanations

    the word "the"

    oai_token-act-pair · gemini-2.0-flash

    beginning

    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
     المعيارى
    -0.66
    StandardCharsets
    -0.52
    expandindo
    -0.50
    LocalizedString
    -0.48
     actionPerformed
    -0.47
     }{@
    -0.46
    SaveChangesAsync
    -0.46
    onActivityResult
    -0.45
    коменду
    -0.44
     ju
    -0.44
    POSITIVE LOGITS
     beginning
    1.23
    beginning
    1.09
    Beginning
    1.05
     Beginning
    0.99
     BEGINNING
    0.91
     begging
    0.77
     begin
    0.75
     beg
    0.71
     very
    0.66
    very
    0.64
    Activations Density 4.907%

    No Known Activations