© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3873
    Prev
    Next
    INDEX
    Explanations

    language used in business contexts particularly involving service and support

    oai_token-act-pair · gemini-2.0-flash

    responding

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     propOrder
    -0.75
    IBOutlet
    -0.73
    ftagPool
    -0.71
    stateMutability
    -0.67
    withIdentifier
    -0.67
    
    -0.66
     uintptr
    -0.65
    RouterModule
    -0.63
     insuffisamment
    -0.62
    DeleteBehavior
    -0.61
    POSITIVE LOGITS
     responsive
    0.59
     Responding
    0.57
     responding
    0.57
     responded
    0.56
    Responding
    0.55
     reacting
    0.54
     responsiveness
    0.54
     quick
    0.51
     réaction
    0.50
     höchste
    0.50
    Activations Density 1.883%

    No Known Activations