Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14444
    Prev
    Next
    INDEX
    Explanations

    instances of code blocks, especially at the end of lines

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ↵↵
    -0.54
    ↵
    -0.47
    нель
    -0.44
    cis
    -0.44
    tı
    -0.43
    @
    -0.42
    Us
    -0.42
     @
    -0.42
    anovich
    -0.41
     diven
    -0.41
    POSITIVE LOGITS
    حوالہ
    0.87
    NUMX
    0.86
    GEBURTSDATUM
    0.85
    IntoConstraints
    0.84
     Réponses
    0.83
    AccessorTable
    0.81
     مشين
    0.79
    Παραπομπές
    0.77
    CloseOperation
    0.76
    ंदीखरीदारी
    0.75
    Activations Density 1.998%

    No Known Activations