© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15882
    Prev
    Next
    INDEX
    Explanations

    words and phrases that include or involve the word "time."

    oai_token-act-pair · gemini-2.0-flash

    over

    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
     فريبيس
    -0.77
    Portály
    -0.74
    @[+][
    -0.71
    دانشنامهٔ
    -0.70
    rungsseite
    -0.70
    .*")]
    -0.67
     hinaus
    -0.66
     ModelExpression
    -0.66
    verwijspagina
    -0.65
    msgTypes
    -0.64
    POSITIVE LOGITS
     over
    2.70
    over
    2.05
     Over
    2.03
    Over
    2.02
     OVER
    1.83
     över
    1.51
    OVER
    1.48
     über
    1.26
    オーバー
    1.23
     ove
    1.13
    Activations Density 3.940%

    No Known Activations