© 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. 3426
    Prev
    Next
    INDEX
    Explanations

    abbreviations, acronyms, and terms used in scientific writing, especially those related to biology, chemistry, and political freedom

    oai_token-act-pair · gemini-2.0-flash

    Scientific and legal documents

    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
     SE
    -0.93
     LA
    -0.85
    SE
    -0.84
     TE
    -0.82
    LA
    -0.81
     RA
    -0.77
     SA
    -0.75
     TA
    -0.73
    TE
    -0.72
    TA
    -0.71
    POSITIVE LOGITS
     INC
    0.82
    IOD
    0.66
     OPT
    0.66
     ION
    0.65
     IMM
    0.64
    INC
    0.62
     Óscar
    0.62
    PRWEB
    0.59
    ICOS
    0.58
    LBL
    0.58
    Activations Density 6.778%

    No Known Activations