© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12804
    Prev
    Next
    INDEX
    Explanations

    references to time passing, often with words like "few," "days", "years", "ago", and "earlier"

    oai_token-act-pair · gemini-2.0-flash

    time periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     kasarigan
    -1.17
    AndEndTag
    -0.94
     <>",
    -0.88
     nakalista
    -0.85
    хьтан
    -0.84
    TypedDataSet
    -0.84
     propOrder
    -0.82
     ivelany
    -0.82
     '\\;'
    -0.81
    achella
    -0.80
    POSITIVE LOGITS
    دخ
    0.43
     niv
    0.41
    aile
    0.40
     ones
    0.39
     beaten
    0.39
     sentito
    0.38
    its
    0.38
    يط
    0.37
    Getter
    0.37
    否
    0.36
    Activations Density 9.706%

    No Known Activations