© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11490
    Prev
    Next
    INDEX
    Explanations

    hedging language like "not" and quantifying words like "any" and "some."

    oai_token-act-pair · gemini-2.0-flash

    negations and expressions of quantity

    np_token-act-pair-logits · gpt-4o-mini

    negation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    DoubleQuotes
    -1.12
    DataAnnotations
    -0.71
    contentLoaded
    -0.66
    +#+
    -0.65
     للمعارف
    -0.64
    :✨
    -0.62
    WSGI
    -0.62
    multer
    -0.62
    balleur
    -0.62
     فريبيس
    -0.60
    POSITIVE LOGITS
     moins
    1.16
     fewer
    1.13
     less
    1.13
     least
    1.05
    Less
    1.03
     menos
    1.02
    least
    0.96
    less
    0.96
     Less
    0.94
     Fewer
    0.94
    Activations Density 1.121%

    No Known Activations