© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11637
    Prev
    Next
    INDEX
    Explanations

    legal jargon and references to legal codes.

    oai_token-act-pair · gemini-2.0-flash

    technical or legal terms

    np_token-act-pair-logits · gpt-4o-mini

    formal writing and citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    <bos>
    -0.75
    abaret
    -0.39
    发表于
    -0.38
    tania
    -0.37
    Upgradeable
    -0.36
    mbros
    -0.36
    btree
    -0.35
     Numerology
    -0.34
    はじめに
    -0.34
    וקה
    -0.34
    POSITIVE LOGITS
     propOrder
    0.56
    UnsafeEnabled
    0.49
     AspNetCore
    0.49
    MemoryWarning
    0.48
    ⓧ
    0.47
    TagMode
    0.46
    windowFixed
    0.44
    BagLayout
    0.43
    rungsseite
    0.43
     contextLoads
    0.43
    Activations Density 14.688%

    No Known Activations