© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5410
    Prev
    Next
    INDEX
    Explanations

    words that express severity of a condition or situation, across a variety of contexts.

    oai_token-act-pair · gemini-2.0-flash

    negative situations/problems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     correctly
    -0.78
     successful
    -0.73
     optimally
    -0.72
     successfully
    -0.71
     adequately
    -0.70
     excellently
    -0.70
     satisfactorily
    -0.69
    correctly
    -0.69
     excellent
    -0.68
    PerformLayout
    -0.68
    POSITIVE LOGITS
     EconPapers
    0.62
     Tapatalk
    0.53
     malade
    0.52
     credibility
    0.52
     enfermo
    0.50
     confidentialité
    0.50
     veracity
    0.49
     inflamed
    0.48
     injured
    0.48
     cansado
    0.47
    Activations Density 11.467%

    No Known Activations