© 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. 5180
    Prev
    Next
    INDEX
    Explanations

    words and phrases pertaining to technical computer programming, medical, and other problem solutioning

    oai_token-act-pair · gemini-2.0-flash

    French words related to aspirations

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

    Non-English text

    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
     createSprite
    -0.69
    تفصیلات
    -0.60
    stini
    -0.57
    ofluorescence
    -0.55
     nowhere
    -0.53
    onicus
    -0.52
    itology
    -0.52
    ulic
    -0.52
    velles
    -0.52
    ้อม
    -0.50
    POSITIVE LOGITS
     sentiers
    0.66
     vœux
    0.59
     sogni
    0.58
     fédé
    0.57
     confronti
    0.57
     nôtre
    0.56
     dépenses
    0.53
    <_>
    0.52
     détail
    0.52
    GraphicsUnit
    0.52
    Activations Density 2.086%

    No Known Activations