© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10621
    Prev
    Next
    INDEX
    Explanations

    XML or HTML tags, especially view, style or div tags

    oai_token-act-pair · gemini-2.0-flash

    CSS code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     EnglishChoose
    -0.60
    __(/*!
    -0.55
    原始内容存档
    -0.52
     newOwner
    -0.51
    hoeddwyd
    -0.51
     running
    -0.51
    CodeAttribute
    -0.49
     interacted
    -0.49
    TargetException
    -0.48
     pri
    -0.48
    POSITIVE LOGITS
     يتيمه
    0.66
     itſelf
    0.52
    ⓧ
    0.51
     himſelf
    0.51
    setVerticalGroup
    0.50
    openqa
    0.49
    mainAxisSize
    0.49
    ArrowToggle
    0.47
    holdet
    0.47
     juſt
    0.47
    Activations Density 3.119%

    No Known Activations