© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11988
    Prev
    Next
    INDEX
    Explanations

    code related to controlling GPIO relays

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'channel'

    np_token-act-pair-logits · gpt-4o-mini

    channels

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    
    -0.71
    uxxxx
    -0.69
     Infórmanos
    -0.69
    VersionUID
    -0.67
    WriteTagHelper
    -0.66
    AndEndTag
    -0.65
     beginnetje
    -0.65
     تضيفلها
    -0.65
    WithIOException
    -0.65
    =$?
    -0.64
    POSITIVE LOGITS
     channels
    0.73
     Channel
    0.69
     channel
    0.69
     Chan
    0.68
    channels
    0.65
    CHANNEL
    0.64
    channel
    0.63
    Channel
    0.63
    Channels
    0.63
    Chan
    0.62
    Activations Density 2.686%

    No Known Activations