© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1113
    Prev
    Next
    INDEX
    Explanations

    html markup tags and related characters

    oai_token-act-pair · gemini-2.0-flash

    HTML

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ><
    -1.14
    "><
    -0.83
    '><
    -0.60
    /><
    -0.59
    ;"><
    -0.57
     חיצוניים
    -0.55
    ')}}"
    -0.50
    pra
    -0.49
    
    -0.49
    leg
    -0.49
    POSITIVE LOGITS
     pleaſure
    0.72
     Administrativna
    0.68
     Baillar
    0.68
    Espèce
    0.65
     continúas
    0.65
     MainAxisSize
    0.61
    ſelves
    0.60
     disambiguazione
    0.59
     ExecuteAsync
    0.57
    nemia
    0.56
    Activations Density 3.860%

    No Known Activations