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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5628
    Prev
    Next
    INDEX
    Explanations

    the word "significantly", sometimes in the context of technical writing

    oai_token-act-pair · gemini-2.0-flash

    significantly

    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
    ere
    -0.72
    .
    -0.69
    ers
    -0.65
    й
    -0.63
    ,
    -0.63
    н
    -0.62
    к
    -0.60
    9
    -0.59
    1
    -0.59
    м
    -0.59
    POSITIVE LOGITS
     propOrder
    1.44
     myſelf
    1.34
    IsContent
    1.30
     himſelf
    1.24
     Efq
    1.22
     الحره
    1.21
    InjectAttribute
    1.20
    ValueStyle
    1.19
     themſelves
    1.15
    ]")]
    1.13
    Activations Density 4.596%

    No Known Activations