© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7715
    Prev
    Next
    INDEX
    Explanations

    the fragment "PAR" together with nearby letters

    oai_token-act-pair · gemini-2.0-flash

    for par

    np_max-act · gemini-2.0-flash
    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
    HandlerContext
    -0.78
    epiece
    -0.72
    setVerticalGroup
    -0.68
    ButterKnife
    -0.68
    borderSide
    -0.66
    isseurs
    -0.65
     Consig
    -0.65
     commutation
    -0.65
    viewDidLoad
    -0.63
    Nek
    -0.63
    POSITIVE LOGITS
    <bos>
    0.90
    Kanpo
    0.65
    Дереккөздер
    0.61
    клопе
    0.60
    ↵↵
    0.59
    Diwedd
    0.58
    Искәрмәләр
    0.57
    Erreferentziak
    0.56
     دیکھیے
    0.56
    তথ্যসূত্র
    0.56
    Activations Density 1.198%

    No Known Activations