© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11391
    Prev
    Next
    INDEX
    Explanations

    dates or time periods, especially months and years, and sometimes related words like "late" or "early"

    oai_token-act-pair · gemini-2.0-flash

    early late

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     geografic
    -0.46
     unborn
    -0.46
     Wikimédia
    -0.45
    ̍
    -0.42
    上次
    -0.41
    зонта
    -0.41
    █
    -0.40
    Unsubscribe
    -0.39
     zuvor
    -0.39
     importing
    -0.39
    POSITIVE LOGITS
     early
    2.88
    early
    2.63
     late
    2.38
    Early
    2.34
     Early
    2.28
     EARLY
    2.23
    EARLY
    2.08
    late
    1.98
    Late
    1.88
     Late
    1.84
    Activations Density 3.560%

    No Known Activations