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. 14906
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to the concept of a right to something, often referring to tickets, vouchers, or entitlements and their transferability

    oai_token-act-pair · gemini-2.0-flash

    transactions

    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
     initComponents
    -0.75
     فريبيس
    -0.68
    IntoConstraints
    -0.65
     переписи
    -0.63
    .*")]
    -0.63
    ConstraintMaker
    -0.59
    +#+#
    -0.58
     مرئيه
    -0.57
    !*\
    -0.57
    MarshalTo
    -0.57
    POSITIVE LOGITS
    posedge
    0.54
    aspectj
    0.53
    SharedDtor
    0.47
    ::_('
    0.44
     discounts
    0.43
    }}">
    0.43
     expense
    0.41
     discounted
    0.41
     ense
    0.41
    Gemeinden
    0.41
    Activations Density 2.678%

    No Known Activations