© 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. 12661
    Prev
    Next
    INDEX
    Explanations

    numbers and words associated with measurement, quantity or order

    oai_token-act-pair · gemini-2.0-flash

    counting/quantities

    np_max-act-logits · gemini-2.0-flash

    one

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     sectors
    -0.84
     phases
    -0.84
     rooms
    -0.81
     domains
    -0.79
     regions
    -0.77
     floors
    -0.76
     stages
    -0.75
     areas
    -0.75
     Phases
    -0.74
     segments
    -0.73
    POSITIVE LOGITS
     bénéfices
    0.81
     vérit
    0.72
     touristes
    0.71
     dieux
    0.71
     travailleurs
    0.71
     médec
    0.71
     dépenses
    0.71
     investissements
    0.71
     récompenses
    0.68
     node
    0.68
    Activations Density 14.749%

    No Known Activations