© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8872
    Prev
    Next
    INDEX
    Explanations

    words relating to infrastructure and planning, especially airports

    oai_token-act-pair · gemini-2.0-flash

    terms related to connections or linkages

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

    connection

    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
     cuire
    -0.54
    PerformLayout
    -0.54
    MultipartFile
    -0.51
    enas
    -0.47
    casm
    -0.47
     chính
    -0.46
    UnifiedTopology
    -0.46
     ब्रेकडाउन
    -0.45
     fuera
    -0.44
    kunft
    -0.44
    POSITIVE LOGITS
     links
    0.91
     linkages
    0.83
     linkage
    0.78
    links
    0.75
     linking
    0.72
     ties
    0.72
     Links
    0.71
    ViewFeatures
    0.71
     forbin
    0.70
     link
    0.69
    Activations Density 3.305%

    No Known Activations