© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6526
    Prev
    Next
    INDEX
    Explanations

    descriptions of shapes and angles

    oai_token-act-pair · gemini-2.0-flash

    technical terms or attributes

    np_token-act-pair-logits · gpt-4o-mini

    shapes and 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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    renderItem
    -0.65
     StatelessWidget
    -0.56
     Reſ
    -0.54
     NSCoder
    -0.54
     bumb
    -0.52
    ffindor
    -0.52
     nho
    -0.50
    艋
    -0.49
    enumi
    -0.49
     Unitarian
    -0.49
    POSITIVE LOGITS
    Diwedd
    0.66
     defaultstate
    0.66
    twimg
    0.65
    Искәрмәләр
    0.63
     transfieras
    0.59
     незавершена
    0.59
     CreateTagHelper
    0.59
    adaptiveStyles
    0.56
     radius
    0.56
     pitch
    0.56
    Activations Density 1.861%

    No Known Activations