© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 9738
    Prev
    Next
    INDEX
    Explanations

    the title of a section or the names of institutions or people

    oai_token-act-pair · gemini-2.0-flash

    About

    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
    ims
    -0.50
    +#+#
    -0.50
     StatelessWidget
    -0.48
    pido
    -0.48
     Zad
    -0.47
    SequentialGroup
    -0.47
    ients
    -0.46
    IBU
    -0.46
     oldValue
    -0.46
     blunt
    -0.45
    POSITIVE LOGITS
    <bos>
    1.18
    ConstraintMaker
    0.69
     Signalez
    0.69
     مرئيه
    0.69
    Хьажоргаш
    0.65
    LEncoder
    0.62
    mybatisplus
    0.61
     समीक्षक
    0.60
    WriteBarrier
    0.60
     wikipagina
    0.59
    Activations Density 1.501%

    No Known Activations