© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 4658
    Prev
    Next
    INDEX
    Explanations

    negations, dates and intensifiers.

    oai_token-act-pair · gemini-2.0-flash

    instances of "until"

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

    until

    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
    oneofs
    -0.65
    #
    -0.63
    GeneratedMessage
    -0.59
    @[+][
    -0.58
    aarrggbb
    -0.56
    ItemBackground
    -0.55
    BufferException
    -0.54
    xase
    -0.54
    argout
    -0.53
    ]=>
    -0.52
    POSITIVE LOGITS
     until
    2.00
    Until
    1.77
     Until
    1.76
     till
    1.74
    until
    1.69
     UNTIL
    1.57
     untill
    1.55
    Till
    1.38
     TILL
    1.35
     til
    1.34
    Activations Density 4.068%

    No Known Activations