© 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. 13336
    Prev
    Next
    INDEX
    Explanations

    a wide range of tokens, including chemical symbols, numbers followed by a period, words related to planning and development, and formatting characters

    oai_token-act-pair · gemini-2.0-flash

    Single letters

    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
    This
    -0.69
     colorés
    -0.68
     chré
    -0.68
     avoient
    -0.67
    We
    -0.66
     aveug
    -0.66
     giapp
    -0.65
     noastre
    -0.64
     käyttää
    -0.62
     abenço
    -0.61
    POSITIVE LOGITS
     O
    0.79
     New
    0.77
     Y
    0.77
     T
    0.76
     F
    0.76
     E
    0.75
     G
    0.75
     P
    0.74
     N
    0.73
     S
    0.72
    Activations Density 5.838%

    No Known Activations