© 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. 15562
    Prev
    Next
    INDEX
    Explanations

    various abbreviations for legal and scientific publications, locations, and organizations

    oai_token-act-pair · gemini-2.0-flash

    Titles and citations

    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
    .
    -0.47
    horabuena
    -0.41
     démocr
    -0.34
     Efq
    -0.34
     définiti
    -0.33
    ształ
    -0.32
    anskje
    -0.32
     réguli
    -0.31
     antemano
    -0.31
    erçe
    -0.31
    POSITIVE LOGITS
    kháu
    0.79
    onaire
    0.71
    +:+
    0.68
    asters
    0.68
    ictions
    0.68
    ams
    0.67
    ['_
    0.67
    ,
    0.67
    aves
    0.66
    eps
    0.65
    Activations Density 10.090%

    No Known Activations