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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6139
    Prev
    Next
    INDEX
    Explanations

    sentences about sewing, especially in the context of art, and personal experiences

    oai_token-act-pair · gemini-2.0-flash

    terms related to competitions or events

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

    fair/project

    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
    +#+#
    -0.79
     Paglinawan
    -0.78
    ItemBackground
    -0.76
    ArgsConstructor
    -0.74
     betweenstory
    -0.74
     linkovi
    -0.72
     للمعارف
    -0.71
     "..\..\..\
    -0.66
    SourceChecksum
    -0.64
    makeText
    -0.62
    POSITIVE LOGITS
     fair
    0.78
     Fair
    0.65
     project
    0.65
     fairs
    0.59
     Project
    0.58
    Project
    0.58
    project
    0.55
    Fair
    0.54
    FAIR
    0.51
     ex
    0.50
    Activations Density 0.953%

    No Known Activations