© 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. 7750
    Prev
    Next
    INDEX
    Explanations

    words related to the service industry and customer service

    oai_token-act-pair · gemini-2.0-flash

    terms related to expertise

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

    Expertise

    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
     oprot
    -0.81
    Spoljašnje
    -0.68
     onCreateView
    -0.66
    parsedMessage
    -0.64
    PerformLayout
    -0.64
     resourceCulture
    -0.63
     EClass
    -0.63
     unknownFields
    -0.61
    sizeCache
    -0.61
    afficheront
    -0.61
    POSITIVE LOGITS
     expert
    0.48
    tal
    0.47
     Talent
    0.47
     specialists
    0.45
     Experten
    0.44
     specialist
    0.43
     key
    0.43
     talented
    0.42
     internal
    0.42
     experts
    0.42
    Activations Density 1.856%

    No Known Activations