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. 16383
    Prev
    Next
    INDEX
    Explanations

    the string `drawable` followed by either `/elf`, `/snow`, `/santa`, or `/reindeer`

    oai_token-act-pair · gemini-2.0-flash

    =@

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.84
     فريبيس
    -0.81
    Geplaatst
    -0.77
    __':
    
    -0.76
    ReusableCell
    -0.71
    ंदीखरीदारी
    -0.71
    \{\\
    -0.69
    TestingModule
    -0.69
    ########.
    -0.66
    MemoryWarning
    -0.65
    POSITIVE LOGITS
    ;->
    0.39
     baga
    0.39
     Duckworth
    0.38
     talent
    0.38
    agara
    0.36
    sizeof
    0.36
    clair
    0.35
     case
    0.35
    philis
    0.35
    wis
    0.35
    Activations Density 0.218%

    No Known Activations