© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12884
    Prev
    Next
    INDEX
    Explanations

    structural elements of research papers such as section headings, figure captions, data descriptions, study references and ethical considerations

    oai_token-act-pair · gemini-2.0-flash

    Research paper sections

    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
    iecie
    -0.69
     صوتيه
    -0.69
    
    -0.67
    =$?
    -0.66
     AssemblyCulture
    -0.65
    onOptions
    -0.64
     CreateTagHelper
    -0.64
    ſelf
    -0.64
     transfieras
    -0.63
    ⓧ
    -0.63
    POSITIVE LOGITS
     FileWriter
    0.54
     Seismic
    0.49
    Processes
    0.48
    sproz
    0.48
     Effects
    0.48
     Causal
    0.47
     Macromolecules
    0.47
     Trend
    0.47
    EFFECT
    0.46
    4
    0.46
    Activations Density 17.230%

    No Known Activations