© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2192
    Prev
    Next
    INDEX
    Explanations

    LaTeX math notation, especially numbers and symbols used in formulas

    oai_token-act-pair · gemini-2.0-flash

    much

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    PerformLayout
    -0.71
    AutoScaleMode
    -0.62
    ...'
    -0.60
    ...»
    -0.59
    ...')
    -0.56
    ..]
    -0.56
    ...',
    -0.56
    :✨
    -0.55
    ...)
    -0.55
     ...)
    -0.54
    POSITIVE LOGITS
     much
    1.08
     Much
    0.88
     MUCH
    0.86
    Much
    0.84
     mucho
    0.83
    much
    0.78
     beaucoup
    0.75
    numerusform
    0.71
    mucho
    0.69
     paljon
    0.69
    Activations Density 1.738%

    No Known Activations