© 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
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8865
    Prev
    Next
    INDEX
    Explanations

    past-tense and descriptive adjectives related to technical processes.

    oai_token-act-pair · gemini-2.0-flash

    Configuration and procedures

    np_max-act · gemini-2.0-flash
    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
    cuma
    -0.43
     fü
    -0.42
    arcoma
    -0.40
    ividual
    -0.39
     Qua
    -0.38
     kiện
    -0.37
    élie
    -0.36
     Instrum
    -0.35
    Bret
    -0.35
    님
    -0.35
    POSITIVE LOGITS
    <bos>
    0.99
    FormTagHelper
    0.74
     becauſe
    0.71
     kasarigan
    0.71
    يكب
    0.69
    ItemBackground
    0.69
     ExecuteAsync
    0.69
     Numerade
    0.69
     itſelf
    0.67
     Wikimedijinoj
    0.66
    Activations Density 2.629%

    No Known Activations