© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6473
    Prev
    Next
    INDEX
    Explanations

    mentions or percentages of statistical data and people

    oai_token-act-pair · gemini-2.0-flash

    Proportions/quantity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    Splitter
    -0.49
     intptr
    -0.47
    tanleria
    -0.46
    nextProps
    -0.45
     دیکھیے
    -0.45
     کیلوم
    -0.44
    zeki
    -0.44
    andExpect
    -0.43
     trò
    -0.43
     simplifié
    -0.42
    POSITIVE LOGITS
     CreateTagHelper
    0.90
    rungsseite
    0.84
     defaultstate
    0.73
    aarrggbb
    0.73
     חיצוניים
    0.69
    abestanden
    0.67
     chi̍t
    0.66
    تقاوى
    0.65
    expandindo
    0.65
    ValueStyle
    0.65
    Activations Density 3.187%

    No Known Activations