© 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. 9348
    Prev
    Next
    INDEX
    Explanations

    text from scientific papers involving equations, formulas, and citations

    oai_token-act-pair · gemini-2.0-flash

    scientific papers

    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
     Wikispecies
    -0.84
    UnsafeEnabled
    -0.73
    IndentedString
    -0.72
     unknownFields
    -0.68
    الإنجليزية
    -0.66
    ]`
    -0.66
     AppModule
    -0.65
     defaultstate
    -0.63
     ControllerBase
    -0.62
    ifrance
    -0.61
    POSITIVE LOGITS
    ificação
    0.50
     mục
    0.48
     وجه
    0.48
     ferons
    0.47
     inversion
    0.47
    ʑ
    0.46
     estándar
    0.46
     standard
    0.45
     Erm
    0.45
    Kontrola
    0.45
    Activations Density 28.970%

    No Known Activations