© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10206
    Prev
    Next
    INDEX
    Explanations

    the word "whilst" in a sentence fragment

    oai_token-act-pair · gemini-2.0-flash

    whilst

    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
     Anſ
    -2.05
     Reſ
    -2.02
     Efq
    -2.00
     myſelf
    -1.99
     itſelf
    -1.95
     Monfieur
    -1.95
     Diſ
    -1.91
     ་་
    -1.87
     Theſe
    -1.80
     Houſe
    -1.78
    POSITIVE LOGITS
     
    1.30
     The
    1.20
     (
    1.15
     and
    1.13
     A
    1.12
     in
    1.12
     M
    1.12
     T
    1.06
     I
    1.06
     K
    1.05
    Activations Density 2.203%

    No Known Activations