© 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. 15336
    Prev
    Next
    INDEX
    Explanations

    angle bracket symbols in what appears to be some type of mathematical notation

    oai_token-act-pair · gemini-2.0-flash

    rangle

    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
     Efq
    -1.58
     ſeveral
    -1.51
     myſelf
    -1.48
     Theſe
    -1.48
     ―――――
    -1.45
    ^(@)
    -1.45
     purpoſe
    -1.43
     iſt
    -1.43
     Jefus
    -1.40
     Majefty
    -1.40
    POSITIVE LOGITS
    <bos>
    1.91
    '
    1.16
    ↵↵
    1.00
    ,
    0.96
     
    0.96
    ’
    0.93
    .
    0.87
    -
    0.86
    ↵
    0.84
      
    0.83
    Activations Density 1.537%

    No Known Activations