© 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. 12590
    Prev
    Next
    INDEX
    Explanations

    XML tags for questions and responses

    oai_token-act-pair · gemini-2.0-flash

    programming snippets

    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
     betweenstory
    -0.65
    ngdoc
    -0.60
     gyhoeddwyd
    -0.54
     kasarigan
    -0.54
    ArgumentParser
    -0.54
    Jîn
    -0.52
     Endor
    -0.51
     oprot
    -0.51
    ysacchar
    -0.51
    Rhestr
    -0.51
    POSITIVE LOGITS
    ile
    0.66
    kse
    0.65
    uste
    0.65
     Steele
    0.65
    trate
    0.63
    IBE
    0.63
    ulle
    0.63
     PSE
    0.63
    lase
    0.63
     Wolfe
    0.62
    Activations Density 11.602%

    No Known Activations