© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14312
    Prev
    Next
    INDEX
    Explanations

    words related to human resources, student learning, and personal/group identity

    oai_token-act-pair · gemini-2.0-flash

    values and beliefs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ecutable
    -0.62
     Benth
    -0.58
    itecture
    -0.58
    StoryboardSegue
    -0.57
    didSet
    -0.56
    WindowConstants
    -0.54
    neur
    -0.54
    enetrable
    -0.53
    InstrumentedTest
    -0.52
    ajuato
    -0.52
    POSITIVE LOGITS
    jspx
    0.58
    InvalidProtocol
    0.53
     perse
    0.52
    DoubleQuotes
    0.52
    Hozzáférés
    0.51
     Dostupné
    0.51
     frames
    0.50
     ivelany
    0.49
    chartInstance
    0.49
     privées
    0.47
    Activations Density 3.905%

    No Known Activations