© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6534
    Prev
    Next
    INDEX
    Explanations

    terms and phrases used in scientific or research papers

    oai_token-act-pair · gemini-2.0-flash

    terms related to methods or strategies

    np_token-act-pair-logits · gpt-4o-mini

    methods

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     autorytatywna
    -0.82
    afficheront
    -0.78
    rungsseite
    -0.75
    AccessorTable
    -0.73
     cherchés
    -0.73
    principalTable
    -0.72
     متعلقه
    -0.71
     AspNetCore
    -0.71
    organisms
    -0.68
     ModelExpression
    -0.67
    POSITIVE LOGITS
     tactics
    0.57
     elements
    0.54
     technique
    0.52
     tactic
    0.52
     ideas
    0.51
     measurements
    0.51
     provisions
    0.51
     features
    0.50
     principles
    0.49
     procedure
    0.49
    Activations Density 9.738%

    No Known Activations