© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11438
    Prev
    Next
    INDEX
    Explanations

    words or phrases relating to academic writing or intellectual concepts.

    oai_token-act-pair · gemini-2.0-flash

    Life events and stories

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    OGND
    -1.23
     myſelf
    -0.98
     Efq
    -0.96
     Мексичка
    -0.93
     ویکی‌پدیا
    -0.92
     Monfieur
    -0.91
     للاسماء
    -0.88
    DoubleQuotes
    -0.87
     ſind
    -0.86
     Theſe
    -0.86
    POSITIVE LOGITS
     is
    0.59
     common
    0.49
     of
    0.49
     Bo
    0.49
     demás
    0.48
    よく
    0.47
     i
    0.45
     surrounding
    0.45
     sus
    0.44
     relevant
    0.44
    Activations Density 33.812%

    No Known Activations