© 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. 15189
    Prev
    Next
    INDEX
    Explanations

    the word 'thread' followed or preceded by other code related words, or complex formal logic

    oai_token-act-pair · gemini-2.0-flash

    Code & data

    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
     (
    -3.28
    (
    -2.36
    （
    -1.85
     ((
    -1.71
     (
    -1.58
    ((
    -1.54
     $(
    -1.52
     ('
    -1.50
     ("
    -1.48
     （
    -1.48
    POSITIVE LOGITS
     kasarigan
    0.60
    PerformLayout
    0.48
    EndGlobalSection
    0.45
    য়
    0.45
     Biôgrafia
    0.44
    SharedDtor
    0.42
    ֥
    0.41
    MessageTagHelper
    0.40
     enfans
    0.39
    Referencie
    0.39
    Activations Density 15.871%

    No Known Activations