© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3587
    Prev
    Next
    INDEX
    Explanations

    years, especially those in the 1900s and 2000s

    oai_token-act-pair · gemini-2.0-flash

    years (1900s, 2000s)

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     three
    -0.72
    3
    -0.68
    三
    -0.60
    0
    -0.59
     trois
    -0.59
    THREE
    -0.56
    三位
    -0.55
     tres
    -0.55
    three
    -0.54
     THREE
    -0.54
    POSITIVE LOGITS
    ngdoc
    0.76
    Архівовано
    0.70
     tartalomajánló
    0.68
     surla
    0.62
    rawDesc
    0.61
    /*++
    0.60
    /−
    0.59
     ¦
    0.58
    +'</
    0.58
    LookAnd
    0.58
    Activations Density 4.176%

    No Known Activations