© 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. 11097
    Prev
    Next
    INDEX
    Explanations

    references to restaurant information within code

    oai_token-act-pair · gemini-2.0-flash

    city data

    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
     Cr
    -0.52
     Signalez
    -0.50
     muka
    -0.50
    jsxFileName
    -0.48
     ث
    -0.48
     Host
    -0.48
    jak
    -0.48
    antu
    -0.47
     Trend
    -0.46
    !*\
    -0.45
    POSITIVE LOGITS
     betweenstory
    0.85
     препратки
    0.79
     itſelf
    0.75
     esternos
    0.73
    utilisons
    0.70
     виправивши
    0.70
     purpoſe
    0.69
     ſtate
    0.67
     NSCoder
    0.66
     varandra
    0.65
    Activations Density 1.795%

    No Known Activations