© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 10163
    Prev
    Next
    INDEX
    Explanations

    seemingly random and not clearly related terms, along with the numbers indicating paragraph beginnings

    oai_token-act-pair · gemini-2.0-flash

    Old English spellings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ponses
    -0.55
    ]:
    -0.47
    %");
    -0.47
    '):
    -0.47
    atisk
    -0.46
    ///</
    -0.45
    bouncycastle
    -0.45
     Us
    -0.45
     she
    -0.44
     chịu
    -0.44
    POSITIVE LOGITS
     houſe
    0.93
     pleaſure
    0.91
     myſelf
    0.85
     poffible
    0.85
     fubject
    0.84
     purpoſe
    0.84
     ſtate
    0.83
     perſon
    0.82
     themſelves
    0.82
     ſever
    0.82
    Activations Density 3.005%

    No Known Activations