© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15949
    Prev
    Next
    INDEX
    Explanations

    file names that look like tables or figures in a scientific paper, especially those associated with PLOS journals

    oai_token-act-pair · gemini-2.0-flash

    0

    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
    -0.97
    RegressionTest
    -0.84
    ValueStyle
    -0.75
    GraphicsUnit
    -0.75
    WebVitals
    -0.73
     nine
    -0.73
    nine
    -0.73
     Réponses
    -0.70
     linkovi
    -0.69
     wireType
    -0.68
    POSITIVE LOGITS
     chré
    0.60
     arché
    0.55
     chrétien
    0.54
     culturelles
    0.54
     preuve
    0.54
     sauvages
    0.54
     fidé
    0.54
     vertes
    0.53
     militaires
    0.52
     légende
    0.50
    Activations Density 12.164%

    No Known Activations