© 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. 10070
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas with symbols like X, C, and inequalities

    oai_token-act-pair · gemini-2.0-flash

    say "X"

    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
     x
    -2.20
    x
    -1.98
     X
    -1.86
    X
    -1.66
     getX
    -1.64
    getX
    -1.51
    xx
    -1.48
    setX
    -1.45
     xx
    -1.44
    Ｘ
    -1.39
    POSITIVE LOGITS
     متعلقه
    0.90
    ]--;
    0.89
    TagMode
    0.89
    principalColumn
    0.82
     שוליים
    0.81
     незавершена
    0.80
    DoubleQuotes
    0.77
    ագրություններ
    0.72
     дописавши
    0.71
     चीज़ों
    0.71
    Activations Density 1.516%

    No Known Activations