© 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. 12003
    Prev
    Next
    INDEX
    Explanations

    the word "wind", especially in the context of power or energy

    oai_token-act-pair · gemini-2.0-flash

    wind

    np_max-act · gemini-2.0-flash

    wind

    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
     ‘
    -0.81
     multi
    -0.60
     an
    -0.60
    ……”
    -0.59
    </h4>
    -0.59
     con
    -0.58
     present
    -0.58
    ”]
    -0.55
    .”
    -0.55
     https
    -0.55
    POSITIVE LOGITS
     Shakspeare
    1.06
     Protestantism
    1.05
     Monfieur
    1.04
     habet
    1.02
     Chriftian
    1.00
    IntoConstraints
    0.98
     Communism
    0.97
     feroit
    0.96
     vectorielle
    0.95
     Czechoslovakia
    0.95
    Activations Density 1.288%

    No Known Activations