© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13299
    Prev
    Next
    INDEX
    Explanations

    scientific references to figures and graphs, and words like "these", which often indicate reference to a later element

    oai_token-act-pair · gemini-2.0-flash

    these

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Efq
    -1.38
     Monfieur
    -1.28
     myſelf
    -1.18
     Theſe
    -1.15
     Majefty
    -1.13
     himſelf
    -1.13
     purpoſe
    -1.12
     Eſ
    -1.10
     Diſ
    -1.10
     auroit
    -1.09
    POSITIVE LOGITS
    ,
    0.70
     so
    0.62
     "
    0.55
     its
    0.55
    ↵↵
    0.55
     $
    0.55
    .
    0.55
     a
    0.55
    jface
    0.54
     van
    0.53
    Activations Density 0.976%

    No Known Activations