© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4975
    Prev
    Next
    INDEX
    Explanations

    instances of past and present tense "to be" verbs

    oai_token-act-pair · gemini-2.0-flash

    articles and common words in sentences

    np_token-act-pair-logits · gpt-4o-mini
    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
    存于互联网档案馆
    -0.59
    TagMode
    -0.54
     adu
    -0.52
    >"+
    -0.51
     kaynağından
    -0.51
    ]--;
    -0.50
    ponses
    -0.49
    mism
    -0.48
    patine
    -0.47
    EndContext
    -0.47
    POSITIVE LOGITS
    ReusableCell
    0.75
    MemoryWarning
    0.64
    óticas
    0.62
     a
    0.60
     that
    0.59
    oredCriteria
    0.59
     such
    0.58
    UTERS
    0.58
     an
    0.56
    envolvimento
    0.54
    Activations Density 0.485%

    No Known Activations