© 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. 9138
    Prev
    Next
    INDEX
    Explanations

    words related to old stories, medicine, and particularly the use of herbs for treatment

    oai_token-act-pair · gemini-2.0-flash

    specialized formatting or entities

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

    medical conditions

    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
     ویکی‌پدیا
    -0.81
     avoient
    -0.60
     Bibliothe
    -0.58
     Meksiku
    -0.57
     &___
    -0.56
     positifs
    -0.55
    otesi
    -0.55
     DataTypes
    -0.53
    évalu
    -0.53
    nivå
    -0.53
    POSITIVE LOGITS
     InputDecoration
    0.68
    مصادر
    0.54
    multirow
    0.54
    出版年
    0.53
    Erstellt
    0.47
    toma
    0.46
     liquid
    0.46
    Influ
    0.45
    bru
    0.45
    輸出
    0.44
    Activations Density 1.236%

    No Known Activations