© 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. 13977
    Prev
    Next
    INDEX
    Explanations

    technical language relevant to different subject matters like legal documents, automotive engineering and scientific research.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "respect"

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

    respect, regard

    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
    Enllaces
    -0.71
    aarrggbb
    -0.65
     jScrollPane
    -0.63
    IonicModule
    -0.59
     GenerationType
    -0.58
     automatiques
    -0.57
     aéri
    -0.54
     Diretto
    -0.51
     médié
    -0.50
     automatique
    -0.50
    POSITIVE LOGITS
     respect
    3.17
    respect
    2.63
     regard
    2.38
     Respect
    2.38
    Respect
    2.20
     RESPECT
    2.14
     respects
    2.11
     regards
    2.08
     respecting
    1.87
    regard
    1.82
    Activations Density 7.749%

    No Known Activations