© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13494
    Prev
    Next
    INDEX
    Explanations

    words related to condemnation, association, or submission

    oai_token-act-pair · gemini-2.0-flash

    save

    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
     apart
    -1.70
    besides
    -1.67
     besides
    -1.64
    apart
    -1.55
     Apart
    -1.50
    Apart
    -1.49
     aside
    -1.43
    Besides
    -1.30
    Aside
    -1.27
     Aside
    -1.27
    POSITIVE LOGITS
     save
    1.35
     Save
    1.14
    save
    1.13
    Save
    1.06
     saves
    1.03
     SAVE
    1.00
     saving
    0.96
    SAVE
    0.94
     Saves
    0.91
     saved
    0.89
    Activations Density 3.103%

    No Known Activations