© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11001
    Prev
    Next
    INDEX
    Explanations

    words or phrases containing "constitution", "super" and "rig"

    oai_token-act-pair · gemini-2.0-flash

    constitution

    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
     simplicity
    -1.34
     accuracy
    -1.31
     robustness
    -1.27
     smoothness
    -1.27
     freshness
    -1.26
     stability
    -1.25
    ness
    -1.25
     efficiency
    -1.25
     reliability
    -1.22
     elegance
    -1.22
    POSITIVE LOGITS
    godic
    0.48
    windowFixed
    0.46
    Fazit
    0.43
    kulu
    0.43
    XtraEditors
    0.42
     mergeFrom
    0.42
    ("~/
    0.42
    Seguro
    0.42
    adecimal
    0.42
    SEGU
    0.40
    Activations Density 1.032%

    No Known Activations