© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10696
    Prev
    Next
    INDEX
    Explanations

    terms related to describing user interface layouts and configuration, and also psychological scoring.

    oai_token-act-pair · gemini-2.0-flash

    character attributes and scores

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     pinulongan
    -0.44
    Slf
    -0.43
    maketitle
    -0.42
    下载附件
    -0.41
    Enllaços
    -0.41
    kriegs
    -0.40
     bruised
    -0.40
     marked
    -0.39
    tonode
    -0.39
    :✨
    -0.39
    POSITIVE LOGITS
     $_"
    0.77
    ttino
    0.74
    RenderAtEndOf
    0.72
    躇
    0.72
     magique
    0.65
     '/':
    0.65
    RegressionTest
    0.64
     Monfieur
    0.63
    herself
    0.63
     igång
    0.63
    Activations Density 7.994%

    No Known Activations