© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12626
    Prev
    Next
    INDEX
    Explanations

    mentions of time periods, specifically focusing on durations in days, weeks, or months.

    oai_token-act-pair · gemini-2.0-flash

    time before or after event

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    IntoConstraints
    -1.08
     onCancelled
    -0.94
     متعلقه
    -0.86
    setVerticalGroup
    -0.80
     NSCoder
    -0.78
     venons
    -0.78
     للاسماء
    -0.77
     Wiktionnaire
    -0.77
    يميديا
    -0.76
     kaynağından
    -0.76
    POSITIVE LOGITS
     thought
    0.52
    出版年
    0.48
    roppo
    0.45
    m
    0.45
     pisos
    0.44
     assumption
    0.43
     Long
    0.41
     Hon
    0.41
     Thought
    0.40
     games
    0.40
    Activations Density 1.460%

    No Known Activations