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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7937
    Prev
    Next
    INDEX
    Explanations

    the word "impossible" and related words like "impractical" and sometimes adverbs that indicate something is hard to do

    oai_token-act-pair · gemini-2.0-flash

    impossible

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.54
    ↵↵
    -1.43
    ↵
    -1.23
    I
    -1.13
     
    -1.10
    '
    -1.09
    1
    -1.03
    i
    -0.99
    E
    -0.98
    T
    -0.97
    POSITIVE LOGITS
    makeConstraints
    1.55
    =$?
    1.48
    parsedMessage
    1.48
    addCriterion
    1.47
     NSCoder
    1.45
    ^(@)
    1.45
    ()")
    1.39
    存于互联网档案馆
    1.39
     JpaRepository
    1.37
     كومونز
    1.36
    Activations Density 1.180%

    No Known Activations