© 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. 11521
    Prev
    Next
    INDEX
    Explanations

    physics or mathematics journal article references with arXiv identifiers

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
    IVEREF
    -0.90
    Portail
    -0.88
    richTextPanel
    -0.86
     saites
    -0.85
     initComponents
    -0.82
    ArrowToggle
    -0.79
     resourceCulture
    -0.76
     Monfieur
    -0.76
     doubtnut
    -0.76
     Inflate
    -0.76
    POSITIVE LOGITS
    e
    0.47
     E
    0.43
     e
    0.42
     L
    0.41
    庁
    0.40
     New
    0.39
     N
    0.38
     åt
    0.38
     said
    0.37
     og
    0.37
    Activations Density 0.920%

    No Known Activations