© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4279
    Prev
    Next
    INDEX
    Explanations

    the word "ending" or "extending" or variations of those words

    oai_token-act-pair · gemini-2.0-flash

    ending

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    AndEndTag
    -0.85
     kasarigan
    -0.77
    Diweddarwch
    -0.72
    PMailer
    -0.67
    andExpect
    -0.67
     الحره
    -0.66
    TypedDataSet
    -0.65
     Monfieur
    -0.65
     sánh
    -0.64
     '\\;'
    -0.63
    POSITIVE LOGITS
     extension
    0.91
     prolongation
    0.87
     extended
    0.85
     extend
    0.84
     continuation
    0.83
     prolon
    0.80
     Extend
    0.80
    Extension
    0.79
     EXTENSION
    0.79
    Extend
    0.78
    Activations Density 2.100%

    No Known Activations