© 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. 10378
    Prev
    Next
    INDEX
    Explanations

    mentions of quantities, especially the numbers two, three, and eight

    oai_token-act-pair · gemini-2.0-flash

    two or three

    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
     two
    -0.81
     three
    -0.78
     a
    -0.75
    two
    -0.73
     trois
    -0.69
     deux
    -0.67
     four
    -0.61
     três
    -0.59
    three
    -0.58
     dois
    -0.57
    POSITIVE LOGITS
    WebVitals
    0.84
     disambiguazione
    0.82
     المعيارى
    0.71
     ſta
    0.70
     nurseries
    0.70
     dictionaries
    0.70
    <bos>
    0.69
     pyramids
    0.68
     unſ
    0.68
     notebooks
    0.68
    Activations Density 7.578%

    No Known Activations