© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6918
    Prev
    Next
    INDEX
    Explanations

    Java code related to text fields and buttons, particularly in the context of a quiz or grading application

    oai_token-act-pair · gemini-2.0-flash

    TF

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     raiſ
    -0.89
     purpoſe
    -0.88
     myſelf
    -0.82
     Efq
    -0.82
     pleaſure
    -0.81
     ſtill
    -0.81
     itſelf
    -0.79
     houſe
    -0.79
     reaſon
    -0.78
     ſtand
    -0.78
    POSITIVE LOGITS
    <bos>
    0.61
     estekak
    0.59
    //
    0.53
     kenal
    0.51
     redor
    0.51
    W
    0.49
    BeginInit
    0.49
    ExtendWith
    0.48
    CrossRef
    0.48
    httphttps
    0.47
    Activations Density 17.619%

    No Known Activations