© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 143
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to academic research.

    oai_token-act-pair · gemini-2.0-flash

    fields of study

    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
    AccessorTable
    -0.96
    ſelf
    -0.93
     Efq
    -0.92
     Theſe
    -0.91
     myſelf
    -0.90
     Majefty
    -0.88
     itſelf
    -0.88
     Houſe
    -0.81
    ſelves
    -0.81
     houſe
    -0.81
    POSITIVE LOGITS
     par
    0.59
     Para
    0.49
     Par
    0.49
     para
    0.48
     Den
    0.48
    Para
    0.47
     I
    0.46
    ’
    0.45
     dei
    0.44
    파
    0.44
    Activations Density 12.258%

    No Known Activations