© 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. 3110
    Prev
    Next
    INDEX
    Explanations

    language typical of scientific publications that describe the study of compounds and their interactions

    oai_token-act-pair · gemini-2.0-flash

    technical jargon or specialized terms

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

    scientific research papers

    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
     colgantes
    -0.50
    mogorov
    -0.48
     internazionali
    -0.48
     électroniques
    -0.46
     libera
    -0.45
     froide
    -0.45
     iguales
    -0.45
     rojas
    -0.45
     internasional
    -0.45
     libere
    -0.44
    POSITIVE LOGITS
    ỡng
    0.76
     MainAxisSize
    0.69
     gynhyrchwyd
    0.65
    awtextra
    0.63
     חיצוניים
    0.63
    XtraEditors
    0.62
    jsonwebtoken
    0.61
    
    0.60
    AddHtmlAttribute
    0.58
    AccessorTable
    0.58
    Activations Density 4.756%

    No Known Activations