© 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. 3523
    Prev
    Next
    INDEX
    Explanations

    the word "exactly", sometimes in combination with the word "The"

    oai_token-act-pair · gemini-2.0-flash

    exactly

    np_max-act · gemini-2.0-flash

    exactly

    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
     this
    -0.73
     the
    -0.73
     it
    -0.65
     a
    -0.62
     pinulongan
    -0.62
    ↵
    -0.60
     Normdatei
    -0.59
    MemoryWarning
    -0.58
     The
    -0.57
     of
    -0.56
    POSITIVE LOGITS
     myſelf
    0.96
     $_"
    0.90
     Theſe
    0.90
     photolibrary
    0.88
     doubtnut
    0.88
    ^(@)
    0.85
     ARXIV
    0.83
     crdi
    0.81
     cdti
    0.80
     himſelf
    0.78
    Activations Density 1.606%

    No Known Activations