© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15606
    Prev
    Next
    INDEX
    Explanations

    LaTeX code related to figures and also the word 'relative'

    oai_token-act-pair · gemini-2.0-flash

    includegraphics

    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
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -1.92
    ↵↵
    -1.54
    '
    -1.48
     
    -1.19
    ↵
    -1.16
    ’
    -1.11
    -
    -1.06
    ,
    -1.04
      
    -1.03
    <eos>
    -1.00
    POSITIVE LOGITS
     Efq
    1.93
     Anſ
    1.77
    ſelf
    1.76
     iſt
    1.73
     ―――――
    1.73
     Diſ
    1.72
     Eſ
    1.71
     myſelf
    1.69
     Reſ
    1.68
     greateſt
    1.68
    Activations Density 1.122%

    No Known Activations