© 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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 8232
    Prev
    Next
    INDEX
    Explanations

    the articles "a" and "the" and the preposition "in"

    oai_token-act-pair · gemini-2.0-flash

    a

    np_max-act · gemini-2.0-flash

    ▁a

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     
    -5.28
    ,
    -4.97
    .
    -4.84
     (
    -4.66
    ↵↵
    -4.47
     in
    -4.03
    ↵
    -4.00
    -
    -3.88
     and
    -3.84
    :
    -3.78
    POSITIVE LOGITS
     myſelf
    9.00
     itſelf
    8.69
     Efq
    8.50
     Monfieur
    8.13
     ―――――
    8.06
     pleaſure
    7.75
     Majefty
    7.75
     Jefus
    7.72
     Theſe
    7.72
     purpoſe
    7.69
    Activations Density 7.927%

    No Known Activations