© 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. 11529
    Prev
    Next
    INDEX
    Explanations

    very verbose, jargon-filled academic writing about quantum physics that contains the word "counterfactual"

    oai_token-act-pair · gemini-2.0-flash

    Academic/scientific texts

    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
    EndGlobal
    -0.59
     مشين
    -0.58
     Ababa
    -0.57
     Minna
    -0.55
    ShowDialog
    -0.54
    atimes
    -0.52
    uminense
    -0.52
    ITest
    -0.51
    uccino
    -0.51
     Terraria
    -0.51
    POSITIVE LOGITS
     EconPapers
    0.60
     فريبيس
    0.53
    ("$.
    0.48
     froh
    0.47
    ględ
    0.46
     diritto
    0.44
     Fitz
    0.44
    EndProject
    0.44
    protoimpl
    0.43
    possession
    0.43
    Activations Density 15.104%

    No Known Activations