© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6488
    Prev
    Next
    INDEX
    Explanations

    C++ code that defines base classes and inheritance

    oai_token-act-pair · gemini-2.0-flash

    base

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    Base
    -1.03
    BASE
    -0.88
    base
    -0.82
     Base
    -0.76
    parsedMessage
    -0.76
    #+#
    -0.75
    XmlAccessorType
    -0.75
     Walkover
    -0.73
     itſelf
    -0.72
     >=",
    -0.70
    POSITIVE LOGITS
    swt
    0.47
     ever
    0.45
     the
    0.45
     pemasangan
    0.45
    MethodManager
    0.45
     o
    0.45
    clearInterval
    0.44
     s
    0.42
     in
    0.42
    னர்
    0.42
    Activations Density 0.296%

    No Known Activations