© 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
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 8718
    Prev
    Next
    INDEX
    Explanations

    instances of the word "month", and the phrases "of the week" or "of the day".

    oai_token-act-pair · gemini-2.0-flash

    Time periods

    np_max-act · gemini-2.0-flash

    time units

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     })}
    -0.90
    Portály
    -0.71
     <<<<<<<<<<<<<<
    -0.69
    })}
    -0.63
    "]
    
    -0.63
    retario
    -0.62
    Geplaatst
    -0.60
    |]
    -0.60
    "],
    
    -0.60
     UnityEditor
    -0.58
    POSITIVE LOGITS
     móvel
    0.69
     lèvres
    0.64
    CodedInputStream
    0.62
    thenReturn
    0.59
     supérieures
    0.59
    ChildScrollView
    0.57
     caccia
    0.57
     vettor
    0.56
     noastre
    0.56
    tableFuture
    0.56
    Activations Density 0.909%

    No Known Activations