© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8419
    Prev
    Next
    INDEX
    Explanations

    instances of "you'll" and other contractions of "you will."

    oai_token-act-pair · gemini-2.0-flash

    say verb

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    WebVitals
    -0.92
    #+#
    -0.81
    providedIn
    -0.81
    InvalidProtocol
    -0.80
     Majefty
    -0.79
     AssemblyCompany
    -0.79
    MLLoader
    -0.78
     ویکی‌پدیای
    -0.77
    MemoryWarning
    -0.76
    StoryboardSegue
    -0.76
    POSITIVE LOGITS
     want
    0.67
     يتيمه
    0.46
    want
    0.45
     contas
    0.43
     thanking
    0.42
     Want
    0.42
     thank
    0.39
     colaboradores
    0.37
    hlander
    0.36
    inar
    0.35
    Activations Density 1.449%

    No Known Activations