© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12826
    Prev
    Next
    INDEX
    Explanations

    words present in mathematical or technical academic papers, along with the word "shredded."

    oai_token-act-pair · gemini-2.0-flash

    Borel transform (math)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    red
    -0.39
    出版年
    -0.38
    zo
    -0.36
     (
    -0.35
    <eos>
    -0.35
    omen
    -0.35
    wo
    -0.35
    ;
    -0.35
    ('_
    -0.35
     letra
    -0.35
    POSITIVE LOGITS
    <bos>
    1.20
     itſelf
    0.98
    脚注の使い方
    0.89
     myſelf
    0.89
     raiſ
    0.89
     ſeveral
    0.87
     pleaſure
    0.86
     Monfieur
    0.84
     ſta
    0.82
    sizeCache
    0.81
    Activations Density 10.530%

    No Known Activations