© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12304
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas, equations, and notation

    oai_token-act-pair · gemini-2.0-flash

    mathematical notation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    -0.91
     
    -0.91
     }}$}
    -0.88
    ^(@)
    -0.84
     itſelf
    -0.84
     Efq
    -0.83
     Theſe
    -0.77
    }{$\
    -0.77
     becauſe
    -0.76
    ſelf
    -0.74
    POSITIVE LOGITS
     \
    1.99
    \
    1.86
    ,\
    1.48
    .\
    1.47
    :\
    1.37
     (\
    1.36
    {\
    1.33
    (\
    1.31
    -\
    1.27
    !\
    1.23
    Activations Density 8.138%

    No Known Activations