© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8375
    Prev
    Next
    INDEX
    Explanations

    phrases containing "play out" or discussing how things work

    oai_token-act-pair · gemini-2.0-flash

    Unfolding events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     lessons
    -1.38
     lesson
    -1.32
     Lessons
    -1.20
    lessons
    -1.20
    Lessons
    -1.16
     Lesson
    -1.13
    lesson
    -1.12
    Lesson
    -1.06
     LESSON
    -1.00
     leçon
    -0.97
    POSITIVE LOGITS
    GraphicsUnit
    0.76
    UnsafeEnabled
    0.75
     unfold
    0.74
    BeginContext
    0.70
    SharedCtor
    0.69
    Personendaten
    0.69
     الاطلاع
    0.66
    oredCriteria
    0.65
    fjspx
    0.64
    béco
    0.62
    Activations Density 0.428%

    No Known Activations