© 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. 11061
    Prev
    Next
    INDEX
    Explanations

    URLs ending in ".co"

    oai_token-act-pair · gemini-2.0-flash

    domain names

    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
     ويكيميديا
    -0.52
    assment
    -0.50
     Suomessa
    -0.50
     ORF
    -0.50
     Attila
    -0.49
    čes
    -0.49
    nets
    -0.46
    createCanvas
    -0.46
     ACM
    -0.46
    IndentedString
    -0.46
    POSITIVE LOGITS
    
    0.65
     الرياضيه
    0.63
     للاسماء
    0.57
     himo
    0.56
    tiary
    0.49
    aternary
    0.47
     cardíaca
    0.47
    ValueStyle
    0.47
    tvguidetime
    0.47
    лтамалар
    0.47
    Activations Density 1.258%

    No Known Activations