© 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. 8187
    Prev
    Next
    INDEX
    Explanations

    text that contains opinions and arguments

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
    expandindo
    -1.33
    PerformLayout
    -1.26
    GEBURTSDATUM
    -1.23
     виправивши
    -1.17
     становника
    -1.17
    parsedMessage
    -1.14
     calendriers
    -1.11
     estekak
    -1.09
    MessageTagHelper
    -1.08
     CreateTagHelper
    -1.07
    POSITIVE LOGITS
     próprio
    0.31
     própria
    0.24
     classiques
    0.24
     flesta
    0.23
     kiedy
    0.23
     próprios
    0.21
     próprias
    0.20
     liknande
    0.20
    0.19
     vorgestellt
    0.19
    Activations Density 47.323%

    No Known Activations