© 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
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6440
    Prev
    Next
    INDEX
    Explanations

    The words "above," "following," and other references to prior statements or information in legal documents.

    oai_token-act-pair · gemini-2.0-flash

    above

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    PhysRevLett
    -0.58
    λικά
    -0.56
     purpoſe
    -0.56
     nhàng
    -0.55
     kolei
    -0.54
    ttino
    -0.54
     Jefus
    -0.54
     faſt
    -0.54
     raiſ
    -0.52
    jednoc
    -0.52
    POSITIVE LOGITS
     BorderRadius
    0.75
    rungsseite
    0.68
     تضيفلها
    0.68
    endregion
    0.68
    MethodManager
    0.65
    исленность
    0.65
    mybatisplus
    0.63
    errHandler
    0.61
    +#+
    0.61
    MemoryWarning
    0.60
    Activations Density 1.194%

    No Known Activations