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. 14161
    Prev
    Next
    INDEX
    Explanations

    words and numbers within mixed-language tech discussions.

    oai_token-act-pair · gemini-2.0-flash

    Foreign languages

    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
    DockStyle
    -0.90
     Theſe
    -0.84
     theſe
    -0.80
     وتسجيلات
    -0.74
     whoſe
    -0.73
     Efq
    -0.73
     myſelf
    -0.72
     Monfieur
    -0.71
     houſe
    -0.71
     becauſe
    -0.70
    POSITIVE LOGITS
    ORROW
    0.46
     horen
    0.44
    évaluateur
    0.44
    thusi
    0.42
    таратура
    0.41
     zien
    0.40
    RegressionTest
    0.39
     så
    0.39
    ]=-
    0.38
     akkor
    0.38
    Activations Density 0.329%

    No Known Activations