© 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. 15361
    Prev
    Next
    INDEX
    Explanations

    the word "pilot" in the context of a study or trial

    oai_token-act-pair · gemini-2.0-flash

    pilot

    np_max-act · gemini-2.0-flash

    pilot

    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
     تضيفلها
    -1.00
    principalTable
    -0.93
     дописавши
    -0.91
    etheless
    -0.90
    tvguidetime
    -0.90
    WebElementEntity
    -0.90
    umblr
    -0.88
     autorytatywna
    -0.87
    jectures
    -0.86
    "],
    -0.84
    POSITIVE LOGITS
    e
    0.86
    1
    0.85
    i
    0.84
    3
    0.84
    2
    0.82
    '
    0.81
    we
    0.78
    4
    0.76
     Shakspeare
    0.76
    y
    0.75
    Activations Density 2.242%

    No Known Activations