© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10535
    Prev
    Next
    INDEX
    Explanations

    positive intensifiers and descriptors, especially related to performance and actions

    oai_token-act-pair · gemini-2.0-flash

    Quick, strong, good

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     heavily
    -1.06
     widely
    -1.00
     badly
    -0.95
     deeply
    -0.95
     strongly
    -0.93
     weakly
    -0.91
     tightly
    -0.90
     lightly
    -0.87
    strongly
    -0.86
     closely
    -0.85
    POSITIVE LOGITS
     quick
    0.79
     strong
    0.68
    Immediate
    0.62
     Immediate
    0.61
    quick
    0.60
     Quick
    0.60
     immediate
    0.60
     good
    0.60
     easy
    0.58
    Quick
    0.57
    Activations Density 2.122%

    No Known Activations