© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15100
    Prev
    Next
    INDEX
    Explanations

    the word "that" along with surrounding words related to scientific writing

    oai_token-act-pair · gemini-2.0-flash

    technical or chemical descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Advoc
    -0.49
     garrafa
    -0.48
     valmist
    -0.46
     côtes
    -0.46
     Drafting
    -0.46
     tradução
    -0.46
    antasy
    -0.45
     pusher
    -0.45
    antastic
    -0.45
     DISEASE
    -0.45
    POSITIVE LOGITS
    ThroughAttribute
    0.86
     يتيمه
    0.79
    ValueStyle
    0.73
    RenderAtEndOf
    0.71
    setVerticalGroup
    0.71
    EnableWeb
    0.70
     StatefulWidget
    0.69
    oredCriteria
    0.67
    protoimpl
    0.66
    Хьажоргаш
    0.65
    Activations Density 3.777%

    No Known Activations