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. 13926
    Prev
    Next
    INDEX
    Explanations

    technical terms and acronyms related to medicine, statistics, or tax

    oai_token-act-pair · gemini-2.0-flash

    Boolean operators

    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
    __':
    
    -1.41
     myſelf
    -1.22
    __":
    
    -1.22
    yntaxException
    -1.20
    NUMX
    -1.20
    SharedDtor
    -1.20
     typelib
    -1.18
    mybatisplus
    -1.18
    ^(@)
    -1.17
    ViewFeatures
    -1.16
    POSITIVE LOGITS
     AND
    1.60
    AND
    1.24
     OR
    1.21
    OR
    0.97
     and
    0.90
    and
    0.88
     And
    0.86
     &&
    0.84
    And
    0.75
    <em>
    0.74
    Activations Density 1.781%

    No Known Activations