© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3065
    Prev
    Next
    INDEX
    Explanations

    phrases expressing emotion and opinions, especially positive reactions and interjections

    oai_token-act-pair · gemini-2.0-flash

    programming and technical terms

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

    punctuation

    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
     кстати
    -0.76
     btw
    -0.73
     BTW
    -0.71
     incidentally
    -0.69
     AspNetCore
    -0.63
    出版年
    -0.61
     Incidentally
    -0.60
    Incident
    -0.57
     linkovi
    -0.55
    apimachinery
    -0.54
    POSITIVE LOGITS
    OrEqualTo
    0.55
    cest
    0.54
     ute
    0.53
    ThroughAttribute
    0.53
     yah
    0.50
    dat
    0.48
     ролях
    0.48
    counter
    0.48
     packageName
    0.48
    usermodel
    0.47
    Activations Density 0.708%

    No Known Activations