© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7403
    Prev
    Next
    INDEX
    Explanations

    descriptions of quality time, particularly time spent with family or on hobbies

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "time"

    np_token-act-pair-logits · gpt-4o-mini

    time

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    AndEndTag
    -0.58
    Hauptartikel
    -0.52
    Geografía
    -0.52
     IBOutlet
    -0.45
    IntoConstraints
    -0.45
     Auer
    -0.45
    bkz
    -0.45
     صوتيه
    -0.44
    وه
    -0.42
    henswürdigkeiten
    -0.41
    POSITIVE LOGITS
     time
    3.50
    time
    2.72
    Time
    2.44
     Time
    2.44
     TIME
    2.39
    TIME
    2.14
    时间
    1.97
     tijd
    1.95
     tiempo
    1.89
     времени
    1.79
    Activations Density 2.737%

    No Known Activations