© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13114
    Prev
    Next
    INDEX
    Explanations

    numerical data, specifically numbers containing digits 1, 2, 3, 4, 5, 6, 7, 8 or 9

    oai_token-act-pair · gemini-2.0-flash

    code and symbols

    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
     McIntosh
    -0.87
     Locust
    -0.86
     Weich
    -0.83
     Osh
    -0.82
     Nich
    -0.81
     Kendall
    -0.81
     Leah
    -0.80
     Slash
    -0.80
    ayah
    -0.79
     McGrath
    -0.77
    POSITIVE LOGITS
    homonymie
    0.59
     dotenv
    0.57
     typelib
    0.55
     ISNI
    0.53
     Massey
    0.52
     Grimal
    0.48
     Eck
    0.48
    plaque
    0.48
    oredCriteria
    0.47
    StoryboardSegue
    0.47
    Activations Density 6.184%

    No Known Activations