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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3490
    Prev
    Next
    INDEX
    Explanations

    a mix of Arabic words, legal jargon, place names, and vocabulary related to indigenous peoples.

    oai_token-act-pair · gemini-2.0-flash

    Mixed code and writing

    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
    Portail
    -0.59
    hatenablog
    -0.56
    Hochspringen
    -0.56
     كومونز
    -0.55
    RectangleBorder
    -0.54
    addContainerGap
    -0.53
    scalatest
    -0.53
    Portale
    -0.50
    ÓN
    -0.49
    interopRequire
    -0.49
    POSITIVE LOGITS
     العالمي
    0.48
    [,]
    0.47
     الجديدة
    0.46
     الاجتماعي
    0.46
     giapp
    0.46
     الغذ
    0.46
     battaglia
    0.45
     alimentaire
    0.45
     princí
    0.44
     immobilier
    0.44
    Activations Density 0.344%

    No Known Activations