© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12888
    Prev
    Next
    INDEX
    Explanations

    the word "As" beginning a clause while also containing a determiner or modifier

    oai_token-act-pair · gemini-2.0-flash

    As

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    <bos>
    -0.83
     
    -0.52
     On
    -0.49
     As
    -0.48
    mat
    -0.47
     however
    -0.46
     Mathews
    -0.44
    եռ
    -0.44
     bit
    -0.44
    am
    -0.43
    POSITIVE LOGITS
     purpoſe
    1.09
     itſelf
    1.00
     Jefus
    0.91
     myſelf
    0.90
     perſon
    0.89
     faſt
    0.87
     Reſ
    0.86
     themſelves
    0.86
     pleaſure
    0.86
    Tembelea
    0.86
    Activations Density 1.949%

    No Known Activations