© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5361
    Prev
    Next
    INDEX
    Explanations

    measurements or enumerated lists in research papers

    oai_token-act-pair · gemini-2.0-flash

    two

    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
    Not in Any Lists

    No Comments

    Negative Logits
     six
    -1.05
     Six
    -1.00
    six
    -0.96
     SIX
    -0.95
     seven
    -0.91
    六
    -0.90
    Six
    -0.90
    SIX
    -0.89
     five
    -0.86
     Seven
    -0.86
    POSITIVE LOGITS
     two
    0.73
    Two
    0.71
     Two
    0.67
    two
    0.61
     iki
    0.61
     deux
    0.55
    TWO
    0.52
    两
    0.52
     Два
    0.51
     dvo
    0.50
    Activations Density 1.496%

    No Known Activations