© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15378
    Prev
    Next
    INDEX
    Explanations

    programming code and/or mathematical notation

    oai_token-act-pair · gemini-2.0-flash

    underscore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     myſelf
    -1.05
     itſelf
    -1.03
    Datuak
    -0.94
     AspNetCore
    -0.93
     Efq
    -0.93
     ſeveral
    -0.93
     houſe
    -0.89
     Theſe
    -0.88
     Monfieur
    -0.87
     Majefty
    -0.86
    POSITIVE LOGITS
     n
    0.63
     
    0.59
    <bos>
    0.59
     bis
    0.59
     “
    0.58
     "
    0.57
     The
    0.57
     c
    0.57
     d
    0.56
     '
    0.56
    Activations Density 20.423%

    No Known Activations