© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6000
    Prev
    Next
    INDEX
    Explanations

    technical language related to scientific topics, specifically in the fields of chemistry, physics, and biology.

    oai_token-act-pair · gemini-2.0-flash

    physical/chemical processes

    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
     дописавши
    -0.80
     sahiptir
    -0.57
    AccessFile
    -0.54
    rophoresis
    -0.52
    الإنجليزية
    -0.51
    Outside
    -0.50
    béco
    -0.50
    AsUp
    -0.50
     varandra
    -0.49
     Outside
    -0.48
    POSITIVE LOGITS
     pushing
    0.67
    Pushing
    0.58
    \{\\
    0.57
     dropping
    0.57
     deep
    0.57
     plugging
    0.54
    tub
    0.53
     catching
    0.53
    printStackTrace
    0.52
     multer
    0.52
    Activations Density 17.542%

    No Known Activations