© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4443
    Prev
    Next
    INDEX
    Explanations

    snippets of words of various length.

    oai_token-act-pair · gemini-2.0-flash

    say "▁" Method used: 2 — because the following tokens mostly start with the whitespace marker ▁ — say "▁"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     varandra
    -1.12
     enfans
    -1.01
     ainfi
    -1.00
     فريبيس
    -0.94
     dieux
    -0.94
     plufieurs
    -0.94
     kvinna
    -0.94
     élevées
    -0.93
     vägen
    -0.92
     feroit
    -0.91
    POSITIVE LOGITS
     sugar
    0.59
     per
    0.57
     whole
    0.57
     self
    0.56
     first
    0.54
     process
    0.54
     long
    0.53
     new
    0.52
     out
    0.52
     level
    0.52
    Activations Density 7.784%

    No Known Activations