© 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. 10037
    Prev
    Next
    INDEX
    Explanations

    the word "opt" followed by other words, likely related to opting in or out of something

    oai_token-act-pair · gemini-2.0-flash

    opt

    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
     autorytatywna
    -1.52
     صوتيه
    -1.38
    InjectAttribute
    -1.27
    AndEndTag
    -1.19
     للمعارف
    -1.19
    SequentialGroup
    -1.17
     AssemblyCulture
    -1.17
    findpost
    -1.16
     CreateTagHelper
    -1.16
    OGND
    -1.16
    POSITIVE LOGITS
    .
    0.68
    -
    0.64
    ,
    0.59
     di
    0.54
    di
    0.53
    </strong>
    0.52
    )
    0.50
    del
    0.49
    0.48
    da
    0.47
    Activations Density 0.462%
    No Known Activations