© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 332
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to official or professional analysis or activities.

    oai_token-act-pair · gemini-2.0-flash

    gamification, interface

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    twimg
    -0.52
    toMap
    -0.44
    Collegamenti
    -0.43
     sqlSession
    -0.42
    alis
    -0.39
    tris
    -0.39
    STORY
    -0.38
    etc
    -0.38
    toJSONString
    -0.38
     Sy
    -0.37
    POSITIVE LOGITS
     OFDb
    0.81
     betweenstory
    0.80
    tvguidetime
    0.79
     تضيفلها
    0.77
    tagHelperRunner
    0.77
    ViewFeatures
    0.76
    NOPQRST
    0.75
    دانشنامهٔ
    0.74
    KURZBESCHREIBUNG
    0.68
     ویکی‌پدیای
    0.67
    Activations Density 10.131%

    No Known Activations