© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 13281
    Prev
    Next
    INDEX
    Explanations

    sentences related to what the author needs or wants to do

    oai_token-act-pair · gemini-2.0-flash

    planning and organizing

    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
    )}</
    -0.77
    webElementXpaths
    -0.74
    "]]
    -0.72
    "]];
    -0.72
    "])
    
    -0.69
    "]);
    
    -0.67
    хьтан
    -0.66
    )]);
    -0.65
    évaluateur
    -0.65
    )];
    
    -0.65
    POSITIVE LOGITS
     focus
    0.48
     pin
    0.47
     mark
    0.44
     jot
    0.44
     fit
    0.43
     dove
    0.43
     strateg
    0.42
     atom
    0.41
     Figure
    0.41
     initComponents
    0.41
    Activations Density 1.752%

    No Known Activations