© 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. 4767
    Prev
    Next
    INDEX
    Explanations

    the word "since", and possibly also words near it.

    oai_token-act-pair · gemini-2.0-flash

    since

    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
     myſelf
    -2.84
     Monfieur
    -2.80
     Efq
    -2.72
     Jefus
    -2.56
     itſelf
    -2.45
     Theſe
    -2.39
     becauſe
    -2.36
     purpoſe
    -2.34
     himſelf
    -2.31
     Majefty
    -2.31
    POSITIVE LOGITS
     
    1.63
     (
    1.42
    <eos>
    1.30
     [
    1.19
    ↵
    1.19
     en
    1.16
    ,
    1.15
     B
    1.14
     $
    1.14
      
    1.13
    Activations Density 1.685%

    No Known Activations