© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9218
    Prev
    Next
    INDEX
    Explanations

    phrases used to concede a point or introduce a contrast.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    nextDouble
    -0.53
     gy
    -0.52
     right
    -0.49
     bal
    -0.49
     ser
    -0.49
    popo
    -0.48
    APON
    -0.48
     bak
    -0.48
     g
    -0.48
     basis
    -0.47
    POSITIVE LOGITS
    脚注の使い方
    0.88
    ांकि
    0.85
    BeginContext
    0.84
    albeit
    0.83
    although
    0.83
     although
    0.83
     Meski
    0.82
    ########.
    0.82
    erdings
    0.80
     embora
    0.79
    Activations Density 0.698%

    No Known Activations