© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2513
    Prev
    Next
    INDEX
    Explanations

    the word "to" followed by "the"

    oai_token-act-pair · gemini-2.0-flash

    phrases related to "to the extent"

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

    the/to

    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
     (&
    -0.52
    openConnection
    -0.52
     betweenstory
    -0.47
     createSlice
    -0.47
    it
    -0.45
    ForRow
    -0.45
    AddTagHelper
    -0.44
    ⓧ
    -0.44
    itorio
    -0.44
    évaluateur
    -0.42
    POSITIVE LOGITS
    NUMX
    0.69
     nỗi
    0.69
     extent
    0.67
    原始内容存档于
    0.64
     مرئيه
    0.63
    ślę
    0.62
     fédé
    0.60
    tagHelperRunner
    0.57
    extent
    0.56
     degree
    0.55
    Activations Density 1.854%

    No Known Activations