© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12909
    Prev
    Next
    INDEX
    Explanations

    first and third person pronouns used in commentary or opinion pieces

    oai_token-act-pair · gemini-2.0-flash

    "have" in different languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    RenderAtEndOf
    -0.89
    تقاوى
    -0.84
     تضيفلها
    -0.74
    istoitu
    -0.63
    exitRule
    -0.63
     समीक्षक
    -0.61
     होता
    -0.60
    AutoresizingMask
    -0.60
     ProtoMessage
    -0.60
     होते
    -0.60
    POSITIVE LOGITS
     has
    0.64
     heeft
    0.56
     đã
    0.56
     telah
    0.53
     està
    0.53
    Jîn
    0.50
     έχει
    0.50
    ంది
    0.48
     hebben
    0.48
     have
    0.47
    Activations Density 2.462%

    No Known Activations