© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3243
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with data analysis and statistics

    oai_token-act-pair · gemini-2.0-flash

    statistical/statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     statistics
    -1.95
     Stat
    -1.91
    Stat
    -1.91
     Statistics
    -1.89
     stat
    -1.84
     statistic
    -1.84
     stats
    -1.79
    Statistics
    -1.76
    stat
    -1.73
     statistical
    -1.73
    POSITIVE LOGITS
    jface
    0.43
    ướng
    0.42
    لات
    0.41
    Toda
    0.40
     deste
    0.40
    undle
    0.40
    undy
    0.39
     endblock
    0.39
     عقد
    0.38
    atibility
    0.38
    Activations Density 8.136%

    No Known Activations