© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5912
    Prev
    Next
    INDEX
    Explanations

    "year" but also sometimes finds related words that include "day", "living", or "sold"

    oai_token-act-pair · gemini-2.0-flash

    year

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     year
    -1.52
    year
    -1.25
    <bos>
    -1.14
     YEAR
    -1.12
    Year
    -1.04
     Year
    -1.00
    YEAR
    -0.91
     année
    -0.80
     yr
    -0.80
     Jahr
    -0.77
    POSITIVE LOGITS
    englanniksi
    0.59
    Vezi
    0.54
    říve
    0.54
    ʁ
    0.53
    ţii
    0.53
    ţilor
    0.53
     "..\..\
    0.51
    '][$
    0.50
     ujednoznacz
    0.50
     insuffisamment
    0.49
    Activations Density 2.706%

    No Known Activations