© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14918
    Prev
    Next
    INDEX
    Explanations

    words in the domain of plant biology dealing with genetics, reproduction, and traits

    oai_token-act-pair · gemini-2.0-flash

    scientific experiments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     فريبيس
    -0.98
     الرياضيه
    -0.95
    WebElementEntity
    -0.95
     avoient
    -0.94
     itſelf
    -0.91
     étoient
    -0.91
     Efq
    -0.90
     Huguen
    -0.88
     greateſt
    -0.88
     myſelf
    -0.87
    POSITIVE LOGITS
     l
    0.64
     
    0.63
     o
    0.63
     s
    0.62
    .
    0.60
    ↵↵
    0.58
     I
    0.58
     in
    0.57
     g
    0.57
     of
    0.56
    Activations Density 5.140%

    No Known Activations