© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10787
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific expressions including variables and equations

    oai_token-act-pair · gemini-2.0-flash

    scientific derivations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    }`}>
    -0.54
    AndroidJUnit
    -0.54
    )}</
    -0.53
    SWIG
    -0.50
    tagHelperRunner
    -0.49
    Tazama
    -0.49
     mathematician
    -0.49
     telefoon
    -0.49
    NUMX
    -0.47
    ParallelGroup
    -0.47
    POSITIVE LOGITS
    uxxxx
    0.63
     exact
    0.60
    رشف
    0.56
    Хьажоргаш
    0.56
     closed
    0.56
     pinulongan
    0.56
    RenderAtEndOf
    0.55
    prüche
    0.53
     nakalista
    0.52
    جة
    0.51
    Activations Density 7.624%

    No Known Activations