© 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. 4137
    Prev
    Next
    INDEX
    Explanations

    the greek letter omega, often found in mathematical formulas

    oai_token-act-pair · gemini-2.0-flash

    omega

    np_max-act · gemini-2.0-flash

    omega

    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
    5
    -0.92
    2
    -0.92
    4
    -0.91
    3
    -0.89
    0
    -0.82
    1
    -0.81
    9
    -0.79
     Baillargeon
    -0.79
    8
    -0.77
    H
    -0.75
    POSITIVE LOGITS
    ugeot
    0.81
    ientôt
    0.79
    pecially
    0.77
    iffance
    0.75
    ratulations
    0.75
    ^(@)
    0.74
    olesale
    0.74
    æa
    0.73
    utterstock
    0.71
    ingtones
    0.70
    Activations Density 1.688%

    No Known Activations